[
 {
  "model": "01-ai-yi-lightning",
  "benchmark": "lmarena-text",
  "score": null,
  "unit": "Elo",
  "provenance": "independent",
  "setting": null,
  "view": "Arena Text overall",
  "rank": 245,
  "rank_population": null,
  "date": "2026-10-08",
  "sources": [
   "https://arena.ai/leaderboard/chat/text"
  ]
 },
 {
  "model": "a-star-meralion-2-10b",
  "benchmark": "audiobench",
  "score": 0.142813,
  "unit": "WER",
  "provenance": "vendor-reported",
  "setting": "Indonesian ASR, average WER by language",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://huggingface.co/MERaLiON/MERaLiON-2-10B"
  ]
 },
 {
  "model": "a-star-meralion-2-10b",
  "benchmark": "sea-helm",
  "score": 58.01,
  "unit": "score",
  "provenance": "maintainer-run",
  "setting": "Indonesian overall; average of 2000 bootstraps",
  "view": "SEA-HELM Indonesian leaderboard, 18 models",
  "rank": 16,
  "rank_population": 18,
  "date": "2026-09-18",
  "uncertainty": "95% CI -1.66 to +1.65",
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://leaderboard.sea-lion.ai/detailed/ID"
  ]
 },
 {
  "model": "a-star-meralion-2-3b",
  "benchmark": "audiobench",
  "score": 0.13195,
  "unit": "WER",
  "provenance": "vendor-reported",
  "setting": "Indonesian ASR, average WER by language",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://huggingface.co/MERaLiON/MERaLiON-2-10B"
  ]
 },
 {
  "model": "abot-world-v0-1",
  "benchmark": "vbench-2-0",
  "score": 55.29,
  "unit": "%",
  "provenance": "maintainer-run",
  "setting": "Creativity score",
  "view": "VBench-2.0",
  "rank": null,
  "rank_population": null,
  "date": "2026-03-21",
  "sources": [
   "https://huggingface.co/spaces/Vchitect/VBench_Leaderboard"
  ]
 },
 {
  "model": "abot-world-v0-1",
  "benchmark": "vbench-2-0",
  "score": 64.47,
  "unit": "%",
  "provenance": "maintainer-run",
  "setting": "Total score",
  "view": "VBench-2.0",
  "rank": 3,
  "rank_population": null,
  "date": "2026-03-21",
  "sources": [
   "https://huggingface.co/spaces/Vchitect/VBench_Leaderboard"
  ]
 },
 {
  "model": "agibot-go-2",
  "benchmark": "genie-sim-3-0",
  "score": 82.9,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "Sim-to-real",
  "view": "AgiBot GO-2 release",
  "rank": null,
  "rank_population": null,
  "date": "2026-04",
  "sources": [
   "https://www.therobotreport.com/agibot-releases-go-2-foundation-model-embodied-ai/"
  ]
 },
 {
  "model": "agibot-go-2",
  "benchmark": "libero-plus",
  "score": 86.6,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "Zero-shot",
  "view": "AgiBot GO-2 release",
  "rank": null,
  "rank_population": null,
  "date": "2026-04",
  "sources": [
   "https://www.therobotreport.com/agibot-releases-go-2-foundation-model-embodied-ai/"
  ]
 },
 {
  "model": "agibot-go-2",
  "benchmark": "libero",
  "score": 98.5,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "Average",
  "view": "AgiBot GO-2 release",
  "rank": null,
  "rank_population": null,
  "date": "2026-04",
  "sources": [
   "https://www.therobotreport.com/agibot-releases-go-2-foundation-model-embodied-ai/"
  ]
 },
 {
  "model": "agibot-go-2",
  "benchmark": "vlabench",
  "score": 47.4,
  "unit": "score",
  "provenance": "vendor-reported",
  "setting": null,
  "view": "AgiBot GO-2 release",
  "rank": null,
  "rank_population": null,
  "date": "2026-04",
  "sources": [
   "https://www.therobotreport.com/agibot-releases-go-2-foundation-model-embodied-ai/"
  ]
 },
 {
  "model": "ai-singapore-gemma-sea-lion-v4-27b-it",
  "benchmark": "sea-helm",
  "score": 64.35,
  "unit": "score",
  "provenance": "maintainer-run",
  "setting": "Checkpoint Gemma-SEA-LION-v4-27B-IT as listed; release view (data last updated 18 Sep 2026); score is the average of 2000 bootstraps",
  "view": "SEA-HELM leaderboard, 58 models, SEA average",
  "rank": null,
  "rank_population": null,
  "date": "2026-09-18",
  "uncertainty": "95% CI [-0.72, +0.71]",
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://leaderboard.sea-lion.ai/detailed/SEA"
  ]
 },
 {
  "model": "ai-singapore-gemma-sea-lion-v4-27b-it",
  "benchmark": "sea-helm",
  "score": 70.55,
  "unit": "score",
  "provenance": "maintainer-run",
  "setting": "Checkpoint Gemma-SEA-LION-v4-27B-IT as listed; release view (data last updated 18 Sep 2026); score is the average of 2000 bootstraps",
  "view": "SEA-HELM leaderboard, 58 models, Indonesian (ID)",
  "rank": null,
  "rank_population": null,
  "date": "2026-09-18",
  "uncertainty": "95% CI [-1.42, +1.46]",
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://leaderboard.sea-lion.ai/detailed/ID"
  ]
 },
 {
  "model": "ai-singapore-gemma-sea-lion-v4-5-e2b-it",
  "benchmark": "sea-helm",
  "score": 59.23,
  "unit": "score",
  "provenance": "maintainer-run",
  "setting": null,
  "view": "SEA-HELM SEA average, open-weight models",
  "rank": null,
  "rank_population": null,
  "date": "2026-09-18",
  "sources": [
   "https://leaderboard.sea-lion.ai/detailed/SEA"
  ],
  "uncertainty": "95% CI [-0.66, +0.67]"
 },
 {
  "model": "ai-singapore-gemma-sea-lion-v4-5-e2b-it",
  "benchmark": "sea-helm",
  "score": 63.96,
  "unit": "score",
  "provenance": "maintainer-run",
  "setting": null,
  "view": "SEA-HELM Indonesian, open-weight models, average of 2,000 bootstraps",
  "rank": null,
  "rank_population": null,
  "date": "2026-09-18",
  "sources": [
   "https://leaderboard.sea-lion.ai/detailed/ID"
  ],
  "uncertainty": "95% CI [-1.38, +1.37]"
 },
 {
  "model": "ai-singapore-nemotron-sea-lion-v4-8-120b-a12b",
  "benchmark": "sea-helm",
  "score": 63.44,
  "unit": "score",
  "provenance": "maintainer-run",
  "setting": null,
  "view": "SEA-HELM SEA average, open-weight models",
  "rank": null,
  "rank_population": null,
  "date": "2026-09-18",
  "sources": [
   "https://leaderboard.sea-lion.ai/detailed/SEA"
  ],
  "uncertainty": "95% CI [-0.63, +0.61]"
 },
 {
  "model": "ai-singapore-nemotron-sea-lion-v4-8-120b-a12b",
  "benchmark": "sea-helm",
  "score": 73.1,
  "unit": "score",
  "provenance": "maintainer-run",
  "setting": null,
  "view": "SEA-HELM Indonesian, open-weight models, average of 2,000 bootstraps",
  "rank": 6,
  "rank_population": null,
  "date": "2026-09-18",
  "sources": [
   "https://leaderboard.sea-lion.ai/detailed/ID"
  ],
  "uncertainty": "95% CI [-1.16, +1.21]"
 },
 {
  "model": "ai-singapore-nemotron-sea-lion-v4-8-30b-a3b",
  "benchmark": "sea-helm",
  "score": 51.57,
  "unit": "score",
  "provenance": "maintainer-run",
  "setting": null,
  "view": "SEA-HELM SEA average, open-weight models",
  "rank": null,
  "rank_population": null,
  "date": "2026-09-18",
  "sources": [
   "https://leaderboard.sea-lion.ai/detailed/SEA"
  ],
  "uncertainty": "95% CI [-0.52, +0.52]"
 },
 {
  "model": "ai-singapore-nemotron-sea-lion-v4-8-30b-a3b",
  "benchmark": "sea-helm",
  "score": 65.87,
  "unit": "score",
  "provenance": "maintainer-run",
  "setting": null,
  "view": "SEA-HELM Indonesian, open-weight models, average of 2,000 bootstraps",
  "rank": null,
  "rank_population": null,
  "date": "2026-09-18",
  "sources": [
   "https://leaderboard.sea-lion.ai/detailed/ID"
  ],
  "uncertainty": "95% CI [-1.29, +1.33]"
 },
 {
  "model": "ai-singapore-qwen-sea-lion-v4-5-27b-it",
  "benchmark": "sea-helm",
  "score": 73.24,
  "unit": "score",
  "provenance": "maintainer-run",
  "setting": null,
  "view": "SEA-HELM SEA average, open-weight models",
  "rank": 4,
  "rank_population": null,
  "date": "2026-09-18",
  "sources": [
   "https://leaderboard.sea-lion.ai/detailed/SEA"
  ],
  "uncertainty": "95% CI [-0.56, +0.57]"
 },
 {
  "model": "ai-singapore-qwen-sea-lion-v4-5-27b-it",
  "benchmark": "sea-helm",
  "score": 76.51,
  "unit": "score",
  "provenance": "maintainer-run",
  "setting": null,
  "view": "SEA-HELM Indonesian, open-weight models, average of 2,000 bootstraps",
  "rank": 4,
  "rank_population": null,
  "date": "2026-09-18",
  "sources": [
   "https://leaderboard.sea-lion.ai/detailed/ID"
  ],
  "uncertainty": "95% CI [-1.23, +1.23]"
 },
 {
  "model": "ai-singapore-qwen-sea-lion-v4-8b-vl",
  "benchmark": "sea-helm",
  "score": 56.41,
  "unit": "score",
  "provenance": "maintainer-run",
  "setting": "Checkpoint Qwen-SEA-LION-v4-8B-VL as listed; release view (data last updated 18 Sep 2026); score is the average of 2000 bootstraps",
  "view": "SEA-HELM leaderboard, 58 models, SEA average",
  "rank": null,
  "rank_population": null,
  "date": "2026-09-18",
  "uncertainty": "95% CI [-0.79, +0.77]",
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://leaderboard.sea-lion.ai/detailed/SEA"
  ]
 },
 {
  "model": "ai-singapore-qwen-sea-lion-v4-8b-vl",
  "benchmark": "sea-helm",
  "score": 67.21,
  "unit": "score",
  "provenance": "maintainer-run",
  "setting": "Checkpoint Qwen-SEA-LION-v4-8B-VL as listed; release view (data last updated 18 Sep 2026); score is the average of 2000 bootstraps",
  "view": "SEA-HELM leaderboard, 58 models, Indonesian (ID)",
  "rank": null,
  "rank_population": null,
  "date": "2026-09-18",
  "uncertainty": "95% CI [-1.64, +1.54]",
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://leaderboard.sea-lion.ai/detailed/ID"
  ]
 },
 {
  "model": "ai-singapore-sea-lion-v4-5-qwen-27b",
  "benchmark": "sea-helm",
  "score": 76.51,
  "unit": "index",
  "provenance": "maintainer-run",
  "setting": "Indonesian",
  "view": "SEA-HELM Indonesian",
  "rank": 4,
  "rank_population": null,
  "date": "2026-09-18",
  "sources": [
   "https://leaderboard.sea-lion.ai/detailed/ID"
  ],
  "unverified": [],
  "uncertainty": "95% CI [-1.23, +1.23]"
 },
 {
  "model": "ai21-labs-jamba-1-5-mini",
  "benchmark": "arc-c",
  "score": 85.7,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2024-08",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://huggingface.co/ai21labs/AI21-Jamba-Mini-1.5"
  ]
 },
 {
  "model": "ai21-labs-jamba-1-5-mini",
  "benchmark": "arena-hard",
  "score": 46.1,
  "unit": "score",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2024-08-22",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://www.ai21.com/blog/announcing-jamba-model-family",
   "https://huggingface.co/ai21labs/AI21-Jamba-Mini-1.5"
  ]
 },
 {
  "model": "ai21-labs-jamba-1-5-mini",
  "benchmark": "bfcl",
  "score": 80.6,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2024-08",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://huggingface.co/ai21labs/AI21-Jamba-Mini-1.5"
  ]
 },
 {
  "model": "ai21-labs-jamba-1-5-mini",
  "benchmark": "gpqa",
  "score": 32.3,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2024-08",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://huggingface.co/ai21labs/AI21-Jamba-Mini-1.5"
  ]
 },
 {
  "model": "ai21-labs-jamba-1-5-mini",
  "benchmark": "gsm8k",
  "score": 75.8,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2024-08",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://huggingface.co/ai21labs/AI21-Jamba-Mini-1.5"
  ]
 },
 {
  "model": "ai21-labs-jamba-1-5-mini",
  "benchmark": "mmlu-pro",
  "score": 42.5,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "CoT",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2024-08",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://huggingface.co/ai21labs/AI21-Jamba-Mini-1.5"
  ]
 },
 {
  "model": "ai21-labs-jamba-1-5-mini",
  "benchmark": "mmlu",
  "score": 69.7,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "CoT",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2024-08",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://huggingface.co/ai21labs/AI21-Jamba-Mini-1.5"
  ]
 },
 {
  "model": "ai21-labs-jamba-1-7-large",
  "benchmark": "aa-intelligence-index",
  "score": 6,
  "unit": "index",
  "provenance": "independent",
  "setting": "asterisk on page",
  "view": "AA leaderboard, 205 current models",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://artificialanalysis.ai/leaderboards/models"
  ]
 },
 {
  "model": "alibaba-happyhorse-1-0",
  "benchmark": "lmarena-text-to-video",
  "score": 1427,
  "unit": "Elo",
  "provenance": "independent",
  "setting": null,
  "view": "LMArena Text-to-Video, updated 21 Sep 2026",
  "rank": 10,
  "rank_population": null,
  "date": "2026-09-21",
  "sources": [
   "https://arena.ai/leaderboard/text-to-video"
  ],
  "uncertainty": "±13"
 },
 {
  "model": "alibaba-happyhorse-1-1",
  "benchmark": "aa-video-t2v",
  "score": 1042,
  "unit": "Elo",
  "provenance": "independent",
  "setting": null,
  "view": "AA Text-to-Video leaderboard",
  "rank": 12,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://artificialanalysis.ai/video/leaderboard/text-to-video"
  ]
 },
 {
  "model": "alibaba-lingjiang-2-0",
  "benchmark": "gift-eval",
  "score": 0.457,
  "unit": "CRPS (geo-mean, normalised to Seasonal Naive)",
  "provenance": "independent",
  "setting": "zero-shot; rank is average CRPS rank",
  "view": "Leaderboard rebuilt from the published raw results, 143 entries covering all 97 configurations",
  "rank": 24,
  "rank_population": 143,
  "date": "2026-10-09",
  "sources": [
   "https://huggingface.co/spaces/Salesforce/GIFT-Eval"
  ],
  "leakage": "no",
  "leakage_note": "Test Leak. column: No (Lingjiang2.0)"
 },
 {
  "model": "alibaba-lingjiang-2-0",
  "benchmark": "gift-eval",
  "score": 0.666,
  "unit": "MASE (geo-mean, normalised to Seasonal Naive)",
  "provenance": "independent",
  "setting": "zero-shot",
  "view": "Leaderboard rebuilt from the published raw results, 143 entries covering all 97 configurations",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-09",
  "sources": [
   "https://huggingface.co/spaces/Salesforce/GIFT-Eval"
  ],
  "leakage": "no",
  "leakage_note": "Test Leak. column: No (Lingjiang2.0)"
 },
 {
  "model": "alibaba-qwen-14b-chat",
  "benchmark": "humaneval",
  "score": 43.9,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "0-shot pass@1",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2023-09",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://huggingface.co/Qwen/Qwen-14B-Chat"
  ]
 },
 {
  "model": "alibaba-qwen-14b-chat",
  "benchmark": "mmlu",
  "score": 66.5,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "5-shot",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2023-09",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://huggingface.co/Qwen/Qwen-14B-Chat"
  ]
 },
 {
  "model": "alibaba-qwen-audio-3-1-tts-plus",
  "benchmark": "aa-tts",
  "score": 1298,
  "unit": "Elo",
  "provenance": "independent",
  "setting": null,
  "view": "AA Text-to-Speech arena, 96 models",
  "rank": 3,
  "rank_population": 96,
  "date": "2026-10-10",
  "sources": [
   "https://artificialanalysis.ai/text-to-speech/leaderboard"
  ]
 },
 {
  "model": "alibaba-qwen-image-2-1",
  "benchmark": "aa-image-t2i-v2-0",
  "score": 1038,
  "unit": "Elo",
  "provenance": "independent",
  "setting": "rank shown as 19-23; top open-weights model per AA FAQ",
  "view": "AA Text-to-Image Arena, overall",
  "rank": 19,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://artificialanalysis.ai/text-to-image/arena/leaderboard-text"
  ]
 },
 {
  "model": "alibaba-qwen-image-2-1",
  "benchmark": "lmarena-text-to-image",
  "score": 1223,
  "unit": "Elo",
  "provenance": "independent",
  "setting": "preliminary",
  "view": "LMArena Text-to-Image, overall, updated 7 Oct 2026",
  "rank": 19,
  "rank_population": null,
  "date": "2026-10-07",
  "sources": [
   "https://arena.ai/leaderboard/text-to-image"
  ],
  "uncertainty": "±7"
 },
 {
  "model": "alibaba-qwen-image-2-1",
  "benchmark": "qwen-image-bench",
  "score": 60.28,
  "unit": "score",
  "provenance": "vendor-reported",
  "setting": "Qwen chart only; methodology unreleased",
  "view": "Qwen vendor chart",
  "rank": null,
  "rank_population": null,
  "date": "2026-09",
  "sources": [
   "https://datanorth.ai/news/qwen-releases-qwen-image-2-1"
  ]
 },
 {
  "model": "alibaba-qwen-image-3-0-pro",
  "benchmark": "aa-image-t2i-v2-0",
  "score": 1088,
  "unit": "Elo",
  "provenance": "independent",
  "setting": "rank shown as 15-17",
  "view": "AA Text-to-Image Arena, overall",
  "rank": 15,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://artificialanalysis.ai/text-to-image/arena/leaderboard-text"
  ]
 },
 {
  "model": "alibaba-qwen-image-3-0-pro",
  "benchmark": "lmarena-text-to-image",
  "score": 1255,
  "unit": "Elo",
  "provenance": "independent",
  "setting": null,
  "view": "LMArena Text-to-Image, overall, updated 7 Oct 2026",
  "rank": 13,
  "rank_population": null,
  "date": "2026-10-07",
  "sources": [
   "https://arena.ai/leaderboard/text-to-image"
  ],
  "uncertainty": "±6"
 },
 {
  "model": "alibaba-qwen-image-3-0-pro",
  "benchmark": "qwen-image-bench",
  "score": 62.36,
  "unit": "score",
  "provenance": "vendor-reported",
  "setting": "Qwen chart only; methodology unreleased",
  "view": "Qwen vendor chart",
  "rank": null,
  "rank_population": null,
  "date": "2026-09",
  "sources": [
   "https://datanorth.ai/news/qwen-releases-qwen-image-2-1"
  ]
 },
 {
  "model": "alibaba-qwen-image-3-0",
  "benchmark": "aa-image-t2i-v2-0",
  "score": 1074,
  "unit": "Elo",
  "provenance": "independent",
  "setting": null,
  "view": "AA Text-to-Image Arena, overall",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://artificialanalysis.ai/text-to-image/arena/leaderboard-text"
  ]
 },
 {
  "model": "alibaba-qwen1-5-110b-chat",
  "benchmark": "mt-bench",
  "score": 8.88,
  "unit": "score",
  "provenance": "vendor-reported",
  "setting": "average score",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2024-04-25",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://qwenlm.github.io/blog/qwen1.5-110b/"
  ]
 },
 {
  "model": "alibaba-qwen1-5-72b",
  "benchmark": "c-eval",
  "score": 84.1,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2024-02-04",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://qwenlm.github.io/blog/qwen1.5/"
  ]
 },
 {
  "model": "alibaba-qwen1-5-72b",
  "benchmark": "cmmlu",
  "score": 83.5,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2024-02-04",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://qwenlm.github.io/blog/qwen1.5/"
  ]
 },
 {
  "model": "alibaba-qwen1-5-72b",
  "benchmark": "gsm8k",
  "score": 79.5,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2024-02-04",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://qwenlm.github.io/blog/qwen1.5/"
  ]
 },
 {
  "model": "alibaba-qwen1-5-72b",
  "benchmark": "humaneval",
  "score": 41.5,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2024-02-04",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://qwenlm.github.io/blog/qwen1.5/"
  ]
 },
 {
  "model": "alibaba-qwen1-5-72b",
  "benchmark": "math",
  "score": 34.1,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2024-02-04",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://qwenlm.github.io/blog/qwen1.5/"
  ]
 },
 {
  "model": "alibaba-qwen1-5-72b",
  "benchmark": "mbpp",
  "score": 53.4,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2024-02-04",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://qwenlm.github.io/blog/qwen1.5/"
  ]
 },
 {
  "model": "alibaba-qwen1-5-72b",
  "benchmark": "mmlu",
  "score": 77.5,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "5-shot",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2024-02-04",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://qwenlm.github.io/blog/qwen1.5/"
  ]
 },
 {
  "model": "alibaba-qwen2-5-32b-instruct",
  "benchmark": "aime-2024",
  "score": 26.7,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "baseline reported in the s1 paper",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2025-01",
  "sources": [
   "https://arxiv.org/html/2501.19393v1"
  ]
 },
 {
  "model": "alibaba-qwen3-5-122b-a10b",
  "benchmark": "sea-helm",
  "score": 74.66,
  "unit": "score",
  "provenance": "maintainer-run",
  "setting": null,
  "view": "SEA-HELM SEA average, open-weight models",
  "rank": 2,
  "rank_population": null,
  "date": "2026-09-18",
  "sources": [
   "https://leaderboard.sea-lion.ai/detailed/SEA"
  ],
  "uncertainty": "95% CI [-0.64, +0.61]"
 },
 {
  "model": "alibaba-qwen3-5-122b-a10b",
  "benchmark": "sea-helm",
  "score": 77.93,
  "unit": "index",
  "provenance": "maintainer-run",
  "setting": "Indonesian",
  "view": "SEA-HELM Indonesian",
  "rank": 3,
  "rank_population": null,
  "date": "2026-09-18",
  "sources": [
   "https://leaderboard.sea-lion.ai/detailed/ID"
  ],
  "unverified": [],
  "uncertainty": "95% CI [-1.29, +1.25]"
 },
 {
  "model": "alibaba-qwen3-5-122b-a10b",
  "benchmark": "sea-helm",
  "score": 77.93,
  "unit": "score",
  "provenance": "maintainer-run",
  "setting": null,
  "view": "SEA-HELM Indonesian, open-weight models, average of 2,000 bootstraps",
  "rank": 3,
  "rank_population": null,
  "date": "2026-09-18",
  "sources": [
   "https://leaderboard.sea-lion.ai/detailed/ID"
  ],
  "uncertainty": "95% CI [-1.29, +1.25]"
 },
 {
  "model": "alibaba-qwen3-5-35b-a3b",
  "benchmark": "sea-helm",
  "score": 73.55,
  "unit": "score",
  "provenance": "maintainer-run",
  "setting": "Checkpoint Qwen3.5-35B-A3B as listed; release view (data last updated 18 Sep 2026); score is the average of 2000 bootstraps",
  "view": "SEA-HELM leaderboard, 58 models, SEA average",
  "rank": null,
  "rank_population": null,
  "date": "2026-09-18",
  "uncertainty": "95% CI [-0.62, +0.60]",
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://leaderboard.sea-lion.ai/detailed/SEA"
  ]
 },
 {
  "model": "alibaba-qwen3-5-35b-a3b",
  "benchmark": "sea-helm",
  "score": 77.55,
  "unit": "score",
  "provenance": "maintainer-run",
  "setting": "Checkpoint Qwen3.5-35B-A3B as listed; release view (data last updated 18 Sep 2026); score is the average of 2000 bootstraps",
  "view": "SEA-HELM leaderboard, 58 models, Indonesian (ID)",
  "rank": null,
  "rank_population": null,
  "date": "2026-09-18",
  "uncertainty": "95% CI [-1.18, +1.21]",
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://leaderboard.sea-lion.ai/detailed/ID"
  ]
 },
 {
  "model": "alibaba-qwen3-5-397b-a17b",
  "benchmark": "gpqa",
  "score": 88.4,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/Qwen/Qwen3.5-397B-A17B"
  ]
 },
 {
  "model": "alibaba-qwen3-5-397b-a17b",
  "benchmark": "mmlu-pro",
  "score": 87.8,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/Qwen/Qwen3.5-397B-A17B"
  ]
 },
 {
  "model": "alibaba-qwen3-5-397b-a17b",
  "benchmark": "swe-bench-verified",
  "score": 76.4,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/Qwen/Qwen3.5-397B-A17B"
  ]
 },
 {
  "model": "alibaba-qwen3-5-4b",
  "benchmark": "mmlu-pro",
  "score": 79.1,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "Not independently verified",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2026-03",
  "sources": [
   "https://rits.shanghai.nyu.edu/ai/qwen-3-5-small-models-9b-parameters-that-beat-120b"
  ],
  "unverified": []
 },
 {
  "model": "alibaba-qwen3-5-4b",
  "benchmark": "sea-helm",
  "score": 63.82,
  "unit": "score",
  "provenance": "maintainer-run",
  "setting": "Checkpoint Qwen3.5-4B as listed; release view (data last updated 18 Sep 2026); score is the average of 2000 bootstraps",
  "view": "SEA-HELM leaderboard, 58 models, SEA average",
  "rank": null,
  "rank_population": null,
  "date": "2026-09-18",
  "uncertainty": "95% CI [-0.65, +0.64]",
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://leaderboard.sea-lion.ai/detailed/SEA"
  ]
 },
 {
  "model": "alibaba-qwen3-5-4b",
  "benchmark": "sea-helm",
  "score": 69.66,
  "unit": "score",
  "provenance": "maintainer-run",
  "setting": "Checkpoint Qwen3.5-4B as listed; release view (data last updated 18 Sep 2026); score is the average of 2000 bootstraps",
  "view": "SEA-HELM leaderboard, 58 models, Indonesian (ID)",
  "rank": null,
  "rank_population": null,
  "date": "2026-09-18",
  "uncertainty": "95% CI [-1.30, +1.32]",
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://leaderboard.sea-lion.ai/detailed/ID"
  ]
 },
 {
  "model": "alibaba-qwen3-5-9b",
  "benchmark": "gpqa-diamond",
  "score": 81.7,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "Not independently verified",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2026-03",
  "sources": [
   "https://rits.shanghai.nyu.edu/ai/qwen-3-5-small-models-9b-parameters-that-beat-120b"
  ],
  "unverified": []
 },
 {
  "model": "alibaba-qwen3-5-9b",
  "benchmark": "mmlu-pro",
  "score": 82.5,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "Not independently verified",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2026-03",
  "sources": [
   "https://rits.shanghai.nyu.edu/ai/qwen-3-5-small-models-9b-parameters-that-beat-120b"
  ],
  "unverified": []
 },
 {
  "model": "alibaba-qwen3-5-9b",
  "benchmark": "sea-helm",
  "score": 69.13,
  "unit": "score",
  "provenance": "maintainer-run",
  "setting": "Checkpoint Qwen3.5-9B as listed; release view (data last updated 18 Sep 2026); score is the average of 2000 bootstraps",
  "view": "SEA-HELM leaderboard, 58 models, SEA average",
  "rank": null,
  "rank_population": null,
  "date": "2026-09-18",
  "uncertainty": "95% CI [-0.64, +0.63]",
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://leaderboard.sea-lion.ai/detailed/SEA"
  ]
 },
 {
  "model": "alibaba-qwen3-5-9b",
  "benchmark": "sea-helm",
  "score": 74.23,
  "unit": "score",
  "provenance": "maintainer-run",
  "setting": "Checkpoint Qwen3.5-9B as listed; release view (data last updated 18 Sep 2026); score is the average of 2000 bootstraps",
  "view": "SEA-HELM leaderboard, 58 models, Indonesian (ID)",
  "rank": null,
  "rank_population": null,
  "date": "2026-09-18",
  "uncertainty": "95% CI [-1.29, +1.28]",
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://leaderboard.sea-lion.ai/detailed/ID"
  ]
 },
 {
  "model": "alibaba-qwen3-6-27b",
  "benchmark": "mmlu-pro",
  "score": 86.2,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/Qwen/Qwen3.6-27B"
  ]
 },
 {
  "model": "alibaba-qwen3-6-27b",
  "benchmark": "sea-helm",
  "score": 74.64,
  "unit": "score",
  "provenance": "maintainer-run",
  "setting": null,
  "view": "SEA-HELM SEA average, open-weight models",
  "rank": null,
  "rank_population": null,
  "date": "2026-09-18",
  "sources": [
   "https://leaderboard.sea-lion.ai/detailed/SEA"
  ],
  "uncertainty": "95% CI [-0.65, +0.60]"
 },
 {
  "model": "alibaba-qwen3-6-27b",
  "benchmark": "sea-helm",
  "score": 77.96,
  "unit": "index",
  "provenance": "maintainer-run",
  "setting": "Indonesian",
  "view": "SEA-HELM Indonesian",
  "rank": 2,
  "rank_population": null,
  "date": "2026-09-18",
  "sources": [
   "https://leaderboard.sea-lion.ai/detailed/ID"
  ],
  "unverified": [],
  "uncertainty": "95% CI [-1.22, +1.20]"
 },
 {
  "model": "alibaba-qwen3-6-27b",
  "benchmark": "sea-helm",
  "score": 77.96,
  "unit": "score",
  "provenance": "maintainer-run",
  "setting": null,
  "view": "SEA-HELM Indonesian, open-weight models, average of 2,000 bootstraps",
  "rank": 2,
  "rank_population": null,
  "date": "2026-09-18",
  "sources": [
   "https://leaderboard.sea-lion.ai/detailed/ID"
  ],
  "uncertainty": "95% CI [-1.22, +1.20]"
 },
 {
  "model": "alibaba-qwen3-6-27b",
  "benchmark": "swe-bench-verified",
  "score": 77.2,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/Qwen/Qwen3.6-27B"
  ]
 },
 {
  "model": "alibaba-qwen3-6-35b-a3b",
  "benchmark": "sea-helm",
  "score": 73.86,
  "unit": "score",
  "provenance": "maintainer-run",
  "setting": "Checkpoint Qwen3.6-35B-A3B as listed; release view (data last updated 18 Sep 2026); score is the average of 2000 bootstraps",
  "view": "SEA-HELM leaderboard, 58 models, SEA average",
  "rank": null,
  "rank_population": null,
  "date": "2026-09-18",
  "uncertainty": "95% CI [-0.60, +0.57]",
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://leaderboard.sea-lion.ai/detailed/SEA"
  ]
 },
 {
  "model": "alibaba-qwen3-6-35b-a3b",
  "benchmark": "sea-helm",
  "score": 77.29,
  "unit": "score",
  "provenance": "maintainer-run",
  "setting": "Checkpoint Qwen3.6-35B-A3B as listed; release view (data last updated 18 Sep 2026); score is the average of 2000 bootstraps",
  "view": "SEA-HELM leaderboard, 58 models, Indonesian (ID)",
  "rank": null,
  "rank_population": null,
  "date": "2026-09-18",
  "uncertainty": "95% CI [-1.22, +1.21]",
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://leaderboard.sea-lion.ai/detailed/ID"
  ]
 },
 {
  "model": "alibaba-qwen3-6-35b-a3b",
  "benchmark": "swe-bench-verified",
  "score": 73.4,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://rits.shanghai.nyu.edu/ai/qwen3-6-35b-a3b-alibaba-open-sources-a-frontier-class-agentic-coder/"
  ]
 },
 {
  "model": "alibaba-qwen3-6-35b-a3b",
  "benchmark": "terminal-bench-2-0",
  "score": 51.5,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://rits.shanghai.nyu.edu/ai/qwen3-6-35b-a3b-alibaba-open-sources-a-frontier-class-agentic-coder/"
  ]
 },
 {
  "model": "alibaba-qwen3-6-plus",
  "benchmark": "swe-bench-verified",
  "score": 78.8,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://www.bitdoze.com/qwen36-ai-coding-agents/",
   "https://leaderboard.steel.dev/leaderboards/swe-bench-verified.md"
  ]
 },
 {
  "model": "alibaba-qwen3-7-max",
  "benchmark": "mmlu-pro",
  "score": 89.6,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": "BenchLM aggregator, top score",
  "rank": 1,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://www.benchlm.ai/benchmarks/mmlu-pro"
  ],
  "unverified": []
 },
 {
  "model": "alibaba-qwen3-7-plus",
  "benchmark": "lmarena-text",
  "score": null,
  "unit": "Elo",
  "provenance": "independent",
  "setting": null,
  "view": "Arena Text overall",
  "rank": 66,
  "rank_population": null,
  "date": "2026-10-08",
  "sources": [
   "https://arena.ai/leaderboard/chat/text"
  ]
 },
 {
  "model": "alibaba-qwen3-8-2-4t-a95b",
  "benchmark": "aa-intelligence-index",
  "score": 40,
  "unit": "index",
  "provenance": "independent",
  "setting": null,
  "view": "AA model page",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://artificialanalysis.ai/models/qwen3-8-2-4t-a95b"
  ]
 },
 {
  "model": "alibaba-qwen3-8-2-4t-a95b",
  "benchmark": "aa-intelligence-index",
  "score": 40,
  "unit": "index",
  "provenance": "independent",
  "setting": "Qwen3.8 2.4T A95B",
  "view": "Artificial Analysis model page",
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://artificialanalysis.ai/models/qwen3-8-2-4t-a95b"
  ]
 },
 {
  "model": "alibaba-qwen3-8-2-4t-a95b",
  "benchmark": "gpqa-diamond",
  "score": 92.6,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B",
   "https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/main/LICENSE"
  ]
 },
 {
  "model": "alibaba-qwen3-8-2-4t-a95b",
  "benchmark": "hle",
  "score": 43.6,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B",
   "https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/main/LICENSE"
  ]
 },
 {
  "model": "alibaba-qwen3-8-2-4t-a95b",
  "benchmark": "swe-bench-pro",
  "score": 67.7,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B",
   "https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/main/LICENSE"
  ]
 },
 {
  "model": "alibaba-qwen3-8-2-4t-a95b",
  "benchmark": "terminal-bench-2-1",
  "score": 86.6,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B",
   "https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/main/LICENSE"
  ]
 },
 {
  "model": "alibaba-qwen3-8-27b",
  "benchmark": "gpqa-diamond",
  "score": 89.2,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/Qwen/Qwen3.8-27B"
  ]
 },
 {
  "model": "alibaba-qwen3-8-27b",
  "benchmark": "livecodebench-v6",
  "score": 90.3,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/Qwen/Qwen3.8-27B"
  ]
 },
 {
  "model": "alibaba-qwen3-8-27b",
  "benchmark": "livecodebench",
  "score": 90.3,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "LiveCodeBench v6",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/Qwen/Qwen3.8-27B"
  ]
 },
 {
  "model": "alibaba-qwen3-8-27b",
  "benchmark": "swe-bench-pro",
  "score": 61.7,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/Qwen/Qwen3.8-27B"
  ]
 },
 {
  "model": "alibaba-qwen3-8-27b",
  "benchmark": "swe-bench-pro",
  "score": 61.7,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/Qwen/Qwen3.8-27B"
  ]
 },
 {
  "model": "alibaba-qwen3-8-27b",
  "benchmark": "terminal-bench-2-1",
  "score": 73,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "Terminus",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/Qwen/Qwen3.8-27B"
  ]
 },
 {
  "model": "alibaba-qwen3-8-flash-next",
  "benchmark": "gpqa-diamond",
  "score": 91.7,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/Qwen/Qwen3.8-Flash-Next"
  ]
 },
 {
  "model": "alibaba-qwen3-8-flash-next",
  "benchmark": "livecodebench-v6",
  "score": 91.9,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/Qwen/Qwen3.8-Flash-Next"
  ]
 },
 {
  "model": "alibaba-qwen3-8-flash-next",
  "benchmark": "sea-helm",
  "score": 73.04,
  "unit": "score",
  "provenance": "maintainer-run",
  "setting": "Checkpoint Qwen3.8-Flash-Next as listed; release view (data last updated 18 Sep 2026); score is the average of 2000 bootstraps",
  "view": "SEA-HELM leaderboard, 58 models, SEA average",
  "rank": null,
  "rank_population": null,
  "date": "2026-09-18",
  "uncertainty": "95% CI [-0.53, +0.53]",
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://leaderboard.sea-lion.ai/detailed/SEA"
  ]
 },
 {
  "model": "alibaba-qwen3-8-flash-next",
  "benchmark": "sea-helm",
  "score": 79.04,
  "unit": "score",
  "provenance": "maintainer-run",
  "setting": "Checkpoint Qwen3.8-Flash-Next as listed; release view (data last updated 18 Sep 2026); score is the average of 2000 bootstraps",
  "view": "SEA-HELM leaderboard, 58 models, Indonesian (ID)",
  "rank": null,
  "rank_population": null,
  "date": "2026-09-18",
  "uncertainty": "95% CI [-1.23, +1.16]",
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://leaderboard.sea-lion.ai/detailed/ID"
  ]
 },
 {
  "model": "alibaba-qwen3-8-flash-next",
  "benchmark": "swe-bench-pro",
  "score": 62.5,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/Qwen/Qwen3.8-Flash-Next"
  ]
 },
 {
  "model": "alibaba-qwen3-8-max",
  "benchmark": "aa-intelligence-index",
  "score": 45,
  "unit": "index",
  "provenance": "independent",
  "setting": "0902",
  "view": "AA leaderboard, 205 current models",
  "rank": 27,
  "rank_population": 205,
  "date": "2026-10-10",
  "sources": [
   "https://artificialanalysis.ai/leaderboards/models"
  ]
 },
 {
  "model": "alibaba-qwen3-8-max",
  "benchmark": "aa-intelligence-index",
  "score": 45,
  "unit": "index",
  "provenance": "independent",
  "setting": "Qwen3.8 Max (0902)",
  "view": "Artificial Analysis model page",
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://artificialanalysis.ai/models/qwen3-8-max"
  ]
 },
 {
  "model": "alibaba-qwen3-8-max",
  "benchmark": "lmarena-text",
  "score": 1483,
  "unit": "Elo",
  "provenance": "independent",
  "setting": null,
  "view": "Arena Text overall",
  "rank": 22,
  "rank_population": null,
  "date": "2026-10-08",
  "sources": [
   "https://arena.ai/leaderboard/chat/text"
  ],
  "uncertainty": "±5"
 },
 {
  "model": "alibaba-qwen3-8-max",
  "benchmark": "lmarena-vision",
  "score": 1301,
  "unit": "Elo",
  "provenance": "independent",
  "setting": null,
  "view": "Arena Vision overall, style control default, 165 models",
  "rank": 2,
  "rank_population": 165,
  "date": "2026-10-09",
  "sources": [
   "https://arena.ai/leaderboard/chat/vision"
  ],
  "uncertainty": "±7"
 },
 {
  "model": "alibaba-qwen3-8-max",
  "benchmark": "osworld-verified",
  "score": 86.1,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "The genealogy notes label the holder open weights; not supported by its sources",
  "view": "BenchLM aggregator, top score",
  "rank": 1,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://www.benchlm.ai/benchmarks/osworld-verified"
  ],
  "unverified": []
 },
 {
  "model": "alibaba-qwen3-8b",
  "benchmark": "sea-helm",
  "score": 60.33,
  "unit": "score",
  "provenance": "maintainer-run",
  "setting": "Checkpoint Qwen3-8B as listed; release view (data last updated 18 Sep 2026); score is the average of 2000 bootstraps",
  "view": "SEA-HELM leaderboard, 58 models, SEA average",
  "rank": null,
  "rank_population": null,
  "date": "2026-09-18",
  "uncertainty": "95% CI [-0.66, +0.67]",
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://leaderboard.sea-lion.ai/detailed/SEA"
  ]
 },
 {
  "model": "alibaba-qwen3-8b",
  "benchmark": "sea-helm",
  "score": 69.36,
  "unit": "score",
  "provenance": "maintainer-run",
  "setting": "Checkpoint Qwen3-8B as listed; release view (data last updated 18 Sep 2026); score is the average of 2000 bootstraps",
  "view": "SEA-HELM leaderboard, 58 models, Indonesian (ID)",
  "rank": null,
  "rank_population": null,
  "date": "2026-09-18",
  "uncertainty": "95% CI [-1.32, +1.36]",
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://leaderboard.sea-lion.ai/detailed/ID"
  ]
 },
 {
  "model": "alibaba-qwen3-asr-0-6b",
  "benchmark": "fleurs",
  "score": 7.92,
  "unit": "WER",
  "provenance": "vendor-reported",
  "setting": "FLEURS Indonesian, Table A.2",
  "view": "Qwen3-ASR technical report",
  "rank": null,
  "rank_population": null,
  "date": "2026-01",
  "sources": [
   "https://arxiv.org/html/2601.21337v2"
  ]
 },
 {
  "model": "alibaba-qwen3-asr-0-6b",
  "benchmark": "open-asr-leaderboard",
  "score": 6.42,
  "unit": "WER",
  "provenance": "maintainer-run",
  "setting": "eight-set macro-average English WER",
  "view": "snapshot 2026-05-06 via benchmarklist",
  "rank": null,
  "rank_population": null,
  "date": "2026-05-06",
  "sources": [
   "https://benchmarklist.com/benchmarks/open_asr_leaderboard/"
  ]
 },
 {
  "model": "alibaba-qwen3-asr-1-7b",
  "benchmark": "fleurs",
  "score": 5.16,
  "unit": "WER",
  "provenance": "vendor-reported",
  "setting": "FLEURS Indonesian, Table A.2",
  "view": "Qwen3-ASR technical report",
  "rank": null,
  "rank_population": null,
  "date": "2026-01",
  "sources": [
   "https://arxiv.org/html/2601.21337v2"
  ]
 },
 {
  "model": "alibaba-qwen3-asr-1-7b",
  "benchmark": "open-asr-leaderboard",
  "score": 5.76,
  "unit": "WER",
  "provenance": "maintainer-run",
  "setting": "eight-set macro-average English WER",
  "view": "snapshot 2026-05-06 via benchmarklist",
  "rank": null,
  "rank_population": null,
  "date": "2026-05-06",
  "sources": [
   "https://benchmarklist.com/benchmarks/open_asr_leaderboard/"
  ]
 },
 {
  "model": "alibaba-qwen3-asr-flash-1208",
  "benchmark": "fleurs",
  "score": 3.65,
  "unit": "WER",
  "provenance": "vendor-reported",
  "setting": "FLEURS Indonesian, Table A.2",
  "view": "Qwen3-ASR technical report",
  "rank": null,
  "rank_population": null,
  "date": "2026-01",
  "sources": [
   "https://arxiv.org/html/2601.21337v2"
  ]
 },
 {
  "model": "alibaba-qwen3-coder-480b-a35b-instruct",
  "benchmark": "swe-bench-pro",
  "score": 38.7,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct"
  ]
 },
 {
  "model": "alibaba-qwen3-coder-480b-a35b-instruct",
  "benchmark": "terminal-bench-2-0",
  "score": 23.9,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct"
  ]
 },
 {
  "model": "alibaba-qwen3-coder-next",
  "benchmark": "swe-bench-pro",
  "score": 44.3,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "scaffold not stated",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/Qwen/Qwen3-Coder-Next"
  ]
 },
 {
  "model": "alibaba-qwen3-coder-next",
  "benchmark": "swe-bench-verified",
  "score": 70.6,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "scaffold not stated",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/Qwen/Qwen3-Coder-Next"
  ]
 },
 {
  "model": "alibaba-qwen3-coder-next",
  "benchmark": "terminal-bench-2-0",
  "score": 36.2,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "scaffold not stated",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/Qwen/Qwen3-Coder-Next"
  ]
 },
 {
  "model": "alibaba-qwen3-embedding-8b",
  "benchmark": "mteb-multilingual",
  "score": 70.58,
  "unit": "score",
  "provenance": "vendor-reported",
  "setting": null,
  "view": "MTEB multilingual (historical)",
  "rank": 1,
  "rank_population": null,
  "date": "2025-06-05",
  "sources": [
   "https://huggingface.co/Qwen/Qwen3-Embedding-8B"
  ]
 },
 {
  "model": "alibaba-qwen3-reranker-8b",
  "benchmark": "mmteb-r",
  "score": 72.94,
  "unit": "score",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/Qwen/Qwen3-Reranker-8B"
  ]
 },
 {
  "model": "alibaba-qwen3-reranker-8b",
  "benchmark": "mteb-r",
  "score": 69.02,
  "unit": "score",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/Qwen/Qwen3-Reranker-8B"
  ]
 },
 {
  "model": "alibaba-qwen3-vl-8b-instruct",
  "benchmark": "sea-helm",
  "score": 56.6,
  "unit": "score",
  "provenance": "maintainer-run",
  "setting": "Checkpoint Qwen3-VL-8B-Instruct as listed; release view (data last updated 18 Sep 2026); score is the average of 2000 bootstraps",
  "view": "SEA-HELM leaderboard, 58 models, SEA average",
  "rank": null,
  "rank_population": null,
  "date": "2026-09-18",
  "uncertainty": "95% CI [-0.79, +0.75]",
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://leaderboard.sea-lion.ai/detailed/SEA"
  ]
 },
 {
  "model": "alibaba-qwen3-vl-8b-instruct",
  "benchmark": "sea-helm",
  "score": 67.46,
  "unit": "score",
  "provenance": "maintainer-run",
  "setting": "Checkpoint Qwen3-VL-8B-Instruct as listed; release view (data last updated 18 Sep 2026); score is the average of 2000 bootstraps",
  "view": "SEA-HELM leaderboard, 58 models, Indonesian (ID)",
  "rank": null,
  "rank_population": null,
  "date": "2026-09-18",
  "uncertainty": "95% CI [-1.55, +1.49]",
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://leaderboard.sea-lion.ai/detailed/ID"
  ]
 },
 {
  "model": "alibaba-qwq-32b-preview",
  "benchmark": "aime",
  "score": 50,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2024-11-28",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://qwenlm.github.io/blog/qwq-32b-preview/"
  ]
 },
 {
  "model": "alibaba-qwq-32b-preview",
  "benchmark": "gpqa",
  "score": 65.2,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2024-11-28",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://qwenlm.github.io/blog/qwq-32b-preview/"
  ]
 },
 {
  "model": "alibaba-qwq-32b-preview",
  "benchmark": "livecodebench",
  "score": 50,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2024-11-28",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://qwenlm.github.io/blog/qwq-32b-preview/"
  ]
 },
 {
  "model": "alibaba-qwq-32b-preview",
  "benchmark": "math-500",
  "score": 90.6,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2024-11-28",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://qwenlm.github.io/blog/qwq-32b-preview/"
  ]
 },
 {
  "model": "alibaba-wan-2-1",
  "benchmark": "vbench",
  "score": 86.22,
  "unit": "%",
  "provenance": "maintainer-run",
  "setting": "Total score; submission-based board",
  "view": "VBench (v1) text-to-video",
  "rank": 6,
  "rank_population": null,
  "date": "2025-02-24",
  "sources": [
   "https://huggingface.co/spaces/Vchitect/VBench_Leaderboard"
  ]
 },
 {
  "model": "alibaba-wan-2-1",
  "benchmark": "vbench",
  "score": 86.67,
  "unit": "%",
  "provenance": "maintainer-run",
  "setting": "Quality score; submission-based board",
  "view": "VBench (v1) text-to-video",
  "rank": null,
  "rank_population": null,
  "date": "2025-02-24",
  "sources": [
   "https://huggingface.co/spaces/Vchitect/VBench_Leaderboard"
  ]
 },
 {
  "model": "alibaba-wan-2-7",
  "benchmark": "lmarena-text-to-video",
  "score": 1337,
  "unit": "Elo",
  "provenance": "independent",
  "setting": "wan2.7-t2v",
  "view": "LMArena Text-to-Video, updated 21 Sep 2026",
  "rank": 20,
  "rank_population": null,
  "date": "2026-09-21",
  "sources": [
   "https://arena.ai/leaderboard/text-to-video"
  ],
  "uncertainty": "±7"
 },
 {
  "model": "alibaba-wan-3-0",
  "benchmark": "aa-video-t2v",
  "score": 1156,
  "unit": "Elo",
  "provenance": "independent",
  "setting": null,
  "view": "AA Text-to-Video leaderboard",
  "rank": 1,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://artificialanalysis.ai/video/leaderboard/text-to-video"
  ]
 },
 {
  "model": "alibaba-wan-3-0",
  "benchmark": "lmarena-text-to-video",
  "score": 1476,
  "unit": "Elo",
  "provenance": "independent",
  "setting": null,
  "view": "LMArena Text-to-Video, updated 21 Sep 2026",
  "rank": 6,
  "rank_population": null,
  "date": "2026-09-21",
  "sources": [
   "https://arena.ai/leaderboard/text-to-video"
  ],
  "uncertainty": "±13"
 },
 {
  "model": "alibaba-z-image-turbo",
  "benchmark": "aa-image-t2i-v2-0",
  "score": 941,
  "unit": "Elo",
  "provenance": "independent",
  "setting": "approximate rank",
  "view": "AA Text-to-Image Arena, overall",
  "rank": 83,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://artificialanalysis.ai/text-to-image/arena/leaderboard-text"
  ]
 },
 {
  "model": "all-hands-ai-openhands-lm-32b-v0-1",
  "benchmark": "swe-bench-verified",
  "score": 37.2,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "OpenHands scaffold",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/OpenHands/openhands-lm-32b-v0.1"
  ]
 },
 {
  "model": "allen-ai-olmo-2-32b",
  "benchmark": "gsm8k",
  "score": 87.6,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": "OLMo-2-0325-32B-Instruct model card",
  "rank": null,
  "rank_population": null,
  "date": "2025-03",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://huggingface.co/allenai/OLMo-2-0325-32B-Instruct"
  ]
 },
 {
  "model": "allen-ai-olmo-2-32b",
  "benchmark": "ifeval",
  "score": 85.6,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": "OLMo-2-0325-32B-Instruct model card",
  "rank": null,
  "rank_population": null,
  "date": "2025-03",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://huggingface.co/allenai/OLMo-2-0325-32B-Instruct"
  ]
 },
 {
  "model": "allen-ai-olmo-2-32b",
  "benchmark": "math",
  "score": 49.7,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": "OLMo-2-0325-32B-Instruct model card",
  "rank": null,
  "rank_population": null,
  "date": "2025-03",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://huggingface.co/allenai/OLMo-2-0325-32B-Instruct"
  ]
 },
 {
  "model": "allen-ai-olmo-2-32b",
  "benchmark": "mmlu",
  "score": 77.3,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": "OLMo-2-0325-32B-Instruct model card",
  "rank": null,
  "rank_population": null,
  "date": "2025-03",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://huggingface.co/allenai/OLMo-2-0325-32B-Instruct"
  ]
 },
 {
  "model": "allen-ai-olmo-3-1-32b-instruct",
  "benchmark": "aa-intelligence-index",
  "score": 6,
  "unit": "index",
  "provenance": "independent",
  "setting": "Intelligence Index v4.3.2; marked estimated (asterisk) on page",
  "view": "AA model page, rank within model class",
  "rank": 34,
  "rank_population": 75,
  "date": "2026-10-11",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://artificialanalysis.ai/models/olmo-3-1-32b-instruct"
  ]
 },
 {
  "model": "allen-ai-olmo-3-1-32b-instruct",
  "benchmark": "aime-2024",
  "score": 67.8,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": "Olmo 3.1 32B Instruct model card",
  "rank": null,
  "rank_population": null,
  "date": "2025-12",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://huggingface.co/allenai/Olmo-3.1-32B-Instruct"
  ]
 },
 {
  "model": "allen-ai-olmo-3-1-32b-instruct",
  "benchmark": "aime-2025",
  "score": 57.9,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": "Olmo 3.1 32B Instruct model card",
  "rank": null,
  "rank_population": null,
  "date": "2025-12",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://huggingface.co/allenai/Olmo-3.1-32B-Instruct"
  ]
 },
 {
  "model": "allen-ai-olmo-3-1-32b-instruct",
  "benchmark": "humaneval-plus",
  "score": 86.7,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": "Olmo 3.1 32B Instruct model card",
  "rank": null,
  "rank_population": null,
  "date": "2025-12",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://huggingface.co/allenai/Olmo-3.1-32B-Instruct"
  ]
 },
 {
  "model": "allen-ai-olmo-3-1-32b-instruct",
  "benchmark": "ifeval",
  "score": 88.8,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": "Olmo 3.1 32B Instruct model card",
  "rank": null,
  "rank_population": null,
  "date": "2025-12",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://huggingface.co/allenai/Olmo-3.1-32B-Instruct"
  ]
 },
 {
  "model": "allen-ai-olmo-3-1-32b-instruct",
  "benchmark": "math",
  "score": 93.4,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": "Olmo 3.1 32B Instruct model card",
  "rank": null,
  "rank_population": null,
  "date": "2025-12",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://huggingface.co/allenai/Olmo-3.1-32B-Instruct"
  ]
 },
 {
  "model": "allen-ai-olmo-3-1-32b-instruct",
  "benchmark": "mmlu",
  "score": 80.9,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": "Olmo 3.1 32B Instruct model card",
  "rank": null,
  "rank_population": null,
  "date": "2025-12",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://huggingface.co/allenai/Olmo-3.1-32B-Instruct"
  ]
 },
 {
  "model": "allen-ai-olmo-3-32b-think",
  "benchmark": "aime-2025",
  "score": 72.5,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/allenai/Olmo-3-32B-Think"
  ]
 },
 {
  "model": "allen-ai-olmo-3-32b-think",
  "benchmark": "ifeval",
  "score": 89,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/allenai/Olmo-3-32B-Think"
  ]
 },
 {
  "model": "allen-ai-olmo-3-32b-think",
  "benchmark": "math",
  "score": 96.1,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/allenai/Olmo-3-32B-Think"
  ]
 },
 {
  "model": "amazon-autogluon-1-5",
  "benchmark": "tabarena",
  "score": 1700,
  "unit": "Elo",
  "provenance": "maintainer-run",
  "setting": "extreme, 4h",
  "view": "All Tasks, no imputation, snapshot 2026-05-06, 59 entries",
  "rank": 1,
  "rank_population": 59,
  "date": "2026-05-06",
  "sources": [
   "https://benchmarklist.com/benchmarks/tabarena_all/",
   "https://benchmarklist.com/benchmarks/tabarena_all/"
  ]
 },
 {
  "model": "amazon-chronos-2",
  "benchmark": "chronos-benchmark-ii",
  "score": null,
  "unit": null,
  "provenance": "vendor-reported",
  "setting": "Claims SOTA zero-shot",
  "view": null,
  "rank": 1,
  "rank_population": null,
  "date": "2025-10-17",
  "sources": [
   "https://huggingface.co/amazon/chronos-2"
  ]
 },
 {
  "model": "amazon-chronos-2",
  "benchmark": "fev-bench",
  "score": null,
  "unit": null,
  "provenance": "vendor-reported",
  "setting": "Claims SOTA",
  "view": null,
  "rank": 1,
  "rank_population": null,
  "date": "2025-10-20",
  "sources": [
   "https://www.amazon.science/blog/introducing-chronos-2-from-univariate-to-universal-forecasting"
  ]
 },
 {
  "model": "amazon-chronos-2",
  "benchmark": "gift-eval",
  "score": null,
  "unit": null,
  "provenance": "vendor-reported",
  "setting": "Claims first among pretrained models, beating TimesFM-2.5 and TiRex",
  "view": null,
  "rank": 1,
  "rank_population": null,
  "date": "2025-10-20",
  "sources": [
   "https://www.amazon.science/blog/introducing-chronos-2-from-univariate-to-universal-forecasting"
  ]
 },
 {
  "model": "amazon-chronos-2",
  "benchmark": "gift-eval",
  "score": 0.485,
  "unit": "CRPS (geo-mean, normalised to Seasonal Naive)",
  "provenance": "independent",
  "setting": "pretrained; rank is average CRPS rank",
  "view": "Leaderboard rebuilt from the published raw results, 143 entries covering all 97 configurations",
  "rank": 57,
  "rank_population": 143,
  "date": "2026-10-09",
  "sources": [
   "https://huggingface.co/spaces/Salesforce/GIFT-Eval"
  ],
  "leakage": "no",
  "leakage_note": "Test Leak. column: No (Chronos-2 (code))"
 },
 {
  "model": "amazon-chronos-2",
  "benchmark": "gift-eval",
  "score": 0.698,
  "unit": "MASE (geo-mean, normalised to Seasonal Naive)",
  "provenance": "independent",
  "setting": "pretrained",
  "view": "Leaderboard rebuilt from the published raw results, 143 entries covering all 97 configurations",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-09",
  "sources": [
   "https://huggingface.co/spaces/Salesforce/GIFT-Eval"
  ],
  "leakage": "no",
  "leakage_note": "Test Leak. column: No (Chronos-2 (code))"
 },
 {
  "model": "amazon-chronos-2",
  "benchmark": "gift-eval",
  "score": 23.5,
  "unit": "mean CRPS rank",
  "provenance": "vendor-reported",
  "setting": "zero-shot foundation-model CRPS rank, lower is better",
  "view": "Toto 2.0 report (Datadog)",
  "rank": null,
  "rank_population": null,
  "date": "2026-06",
  "sources": [
   "https://arxiv.org/pdf/2605.20119"
  ]
 },
 {
  "model": "amazon-nova-2-0-omni",
  "benchmark": "aa-intelligence-index",
  "score": 14,
  "unit": "index",
  "provenance": "independent",
  "setting": "asterisk on page",
  "view": "AA leaderboard, 205 current models",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://artificialanalysis.ai/leaderboards/models"
  ]
 },
 {
  "model": "amazon-nova-2-0-pro-preview",
  "benchmark": "aa-intelligence-index",
  "score": 14,
  "unit": "index",
  "provenance": "independent",
  "setting": "medium; asterisk on page",
  "view": "AA leaderboard, 205 current models",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://artificialanalysis.ai/leaderboards/models"
  ]
 },
 {
  "model": "ant-group-xihe-ultra",
  "benchmark": "gift-eval",
  "score": 0.488,
  "unit": "CRPS (geo-mean, normalised to Seasonal Naive)",
  "provenance": "independent",
  "setting": "zero-shot; rank is average CRPS rank",
  "view": "Leaderboard rebuilt from the published raw results, 143 entries covering all 97 configurations",
  "rank": 73,
  "rank_population": 143,
  "date": "2026-10-09",
  "sources": [
   "https://huggingface.co/spaces/Salesforce/GIFT-Eval"
  ],
  "leakage": "no",
  "leakage_note": "Test Leak. column: No (Xihe-ultra)"
 },
 {
  "model": "ant-group-xihe-ultra",
  "benchmark": "gift-eval",
  "score": 0.701,
  "unit": "MASE (geo-mean, normalised to Seasonal Naive)",
  "provenance": "independent",
  "setting": "zero-shot",
  "view": "Leaderboard rebuilt from the published raw results, 143 entries covering all 97 configurations",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-09",
  "sources": [
   "https://huggingface.co/spaces/Salesforce/GIFT-Eval"
  ],
  "leakage": "no",
  "leakage_note": "Test Leak. column: No (Xihe-ultra)"
 },
 {
  "model": "ant-group-xihe-ultra",
  "benchmark": "gift-eval",
  "score": 29.5,
  "unit": "mean CRPS rank",
  "provenance": "vendor-reported",
  "setting": "zero-shot foundation-model CRPS rank, lower is better",
  "view": "Toto 2.0 report (Datadog)",
  "rank": null,
  "rank_population": null,
  "date": "2026-06",
  "sources": [
   "https://arxiv.org/pdf/2605.20119"
  ]
 },
 {
  "model": "anthropic-claude-3-5-sonnet-oct-24",
  "benchmark": "osworld",
  "score": 14.9,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "screenshot-only",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2024-10-22",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://www.anthropic.com/news/3-5-models-and-computer-use"
  ]
 },
 {
  "model": "anthropic-claude-3-5-sonnet-oct-24",
  "benchmark": "osworld",
  "score": 22,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "screenshot-only, more steps allowed",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2024-10-22",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://www.anthropic.com/news/3-5-models-and-computer-use"
  ]
 },
 {
  "model": "anthropic-claude-3-5-sonnet-oct-24",
  "benchmark": "swe-bench-verified",
  "score": 49,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2024-10-22",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://www.anthropic.com/news/3-5-models-and-computer-use"
  ]
 },
 {
  "model": "anthropic-claude-3-5-sonnet-oct-24",
  "benchmark": "tau-bench",
  "score": 46,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "airline domain",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2024-10-22",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://www.anthropic.com/news/3-5-models-and-computer-use"
  ]
 },
 {
  "model": "anthropic-claude-3-5-sonnet-oct-24",
  "benchmark": "tau-bench",
  "score": 69.2,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "retail domain",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2024-10-22",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://www.anthropic.com/news/3-5-models-and-computer-use"
  ]
 },
 {
  "model": "anthropic-claude-3-opus",
  "benchmark": "ai2d",
  "score": 88.1,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "test set",
  "view": "Claude 3 model card, Table 1 and vision table",
  "rank": null,
  "rank_population": null,
  "date": "2024-03",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://www-cdn.anthropic.com/de8ba9b01c9ab7cbabf5c33b80b7bbc618857627/Model_Card_Claude_3.pdf"
  ]
 },
 {
  "model": "anthropic-claude-3-opus",
  "benchmark": "gpqa-diamond",
  "score": 50.4,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "0-shot CoT",
  "view": "Claude 3 model card, Table 1 and vision table",
  "rank": null,
  "rank_population": null,
  "date": "2024-03",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://www-cdn.anthropic.com/de8ba9b01c9ab7cbabf5c33b80b7bbc618857627/Model_Card_Claude_3.pdf"
  ]
 },
 {
  "model": "anthropic-claude-3-opus",
  "benchmark": "gsm8k",
  "score": 95,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "0-shot CoT",
  "view": "Claude 3 model card, Table 1 and vision table",
  "rank": null,
  "rank_population": null,
  "date": "2024-03",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://www-cdn.anthropic.com/de8ba9b01c9ab7cbabf5c33b80b7bbc618857627/Model_Card_Claude_3.pdf"
  ]
 },
 {
  "model": "anthropic-claude-3-opus",
  "benchmark": "humaneval",
  "score": 84.9,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "0-shot",
  "view": "Claude 3 model card, Table 1 and vision table",
  "rank": null,
  "rank_population": null,
  "date": "2024-03",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://www-cdn.anthropic.com/de8ba9b01c9ab7cbabf5c33b80b7bbc618857627/Model_Card_Claude_3.pdf"
  ]
 },
 {
  "model": "anthropic-claude-3-opus",
  "benchmark": "mgsm",
  "score": 90.7,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "0-shot",
  "view": "Claude 3 model card, Table 1 and vision table",
  "rank": null,
  "rank_population": null,
  "date": "2024-03",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://www-cdn.anthropic.com/de8ba9b01c9ab7cbabf5c33b80b7bbc618857627/Model_Card_Claude_3.pdf"
  ]
 },
 {
  "model": "anthropic-claude-3-sonnet",
  "benchmark": "ai2d",
  "score": 88.7,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "test set",
  "view": "Claude 3 model card, Table 1 and vision table",
  "rank": null,
  "rank_population": null,
  "date": "2024-03",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://www-cdn.anthropic.com/de8ba9b01c9ab7cbabf5c33b80b7bbc618857627/Model_Card_Claude_3.pdf"
  ]
 },
 {
  "model": "anthropic-claude-3-sonnet",
  "benchmark": "gpqa-diamond",
  "score": 40.4,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "0-shot CoT",
  "view": "Claude 3 model card, Table 1 and vision table",
  "rank": null,
  "rank_population": null,
  "date": "2024-03",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://www-cdn.anthropic.com/de8ba9b01c9ab7cbabf5c33b80b7bbc618857627/Model_Card_Claude_3.pdf"
  ]
 },
 {
  "model": "anthropic-claude-3-sonnet",
  "benchmark": "gsm8k",
  "score": 92.3,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "0-shot CoT",
  "view": "Claude 3 model card, Table 1 and vision table",
  "rank": null,
  "rank_population": null,
  "date": "2024-03",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://www-cdn.anthropic.com/de8ba9b01c9ab7cbabf5c33b80b7bbc618857627/Model_Card_Claude_3.pdf"
  ]
 },
 {
  "model": "anthropic-claude-3-sonnet",
  "benchmark": "humaneval",
  "score": 73,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "0-shot",
  "view": "Claude 3 model card, Table 1 and vision table",
  "rank": null,
  "rank_population": null,
  "date": "2024-03",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://www-cdn.anthropic.com/de8ba9b01c9ab7cbabf5c33b80b7bbc618857627/Model_Card_Claude_3.pdf"
  ]
 },
 {
  "model": "anthropic-claude-fable-5-1",
  "benchmark": "aa-intelligence-index",
  "score": 53,
  "unit": "index",
  "provenance": "independent",
  "setting": "max",
  "view": "AA leaderboard, 205 current models",
  "rank": 5,
  "rank_population": 205,
  "date": "2026-10-10",
  "sources": [
   "https://artificialanalysis.ai/leaderboards/models"
  ]
 },
 {
  "model": "anthropic-claude-fable-5-1",
  "benchmark": "benchlm-composite",
  "score": 82,
  "unit": "index",
  "provenance": "vendor-reported",
  "setting": null,
  "view": "benchlm.ai frontier top 6",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-09",
  "sources": [
   "https://benchlm.ai/frontier-ai-models"
  ]
 },
 {
  "model": "anthropic-claude-fable-5-1",
  "benchmark": "gdpval-aa-v2-1",
  "score": 1735,
  "unit": "Elo",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://vpsranking.com/news/ai/ai-2026-09-22-anthropic-claude-opus-5-5/"
  ]
 },
 {
  "model": "anthropic-claude-fable-5-1",
  "benchmark": "hle",
  "score": 65,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "Table mixes runs with and without tools",
  "view": "BenchLM aggregator, top score",
  "rank": 1,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://www.benchlm.ai/benchmarks/hle"
  ],
  "unverified": []
 },
 {
  "model": "anthropic-claude-fable-5-1",
  "benchmark": "ioi",
  "score": 90.78,
  "unit": "%",
  "provenance": "independent",
  "setting": "Vals.ai, max effort",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://vals.ai/models/anthropic_claude-fable-5-1"
  ],
  "uncertainty": "±4.65"
 },
 {
  "model": "anthropic-claude-fable-5-1",
  "benchmark": "livecodebench",
  "score": 90.5,
  "unit": "%",
  "provenance": "independent",
  "setting": "Vals-run variant",
  "view": "Vals.ai run shown on BenchLM",
  "rank": 1,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://benchlm.ai/coding"
  ],
  "unverified": []
 },
 {
  "model": "anthropic-claude-fable-5-1",
  "benchmark": "livecodebench",
  "score": 90.52,
  "unit": "%",
  "provenance": "independent",
  "setting": "Vals.ai, max effort",
  "view": null,
  "rank": 1,
  "rank_population": 143,
  "date": null,
  "sources": [
   "https://vals.ai/models/anthropic_claude-fable-5-1"
  ],
  "uncertainty": "±0.86"
 },
 {
  "model": "anthropic-claude-fable-5-1",
  "benchmark": "lmarena-text",
  "score": 1501,
  "unit": "Elo",
  "provenance": "independent",
  "setting": "max",
  "view": "Arena Text overall",
  "rank": 6,
  "rank_population": null,
  "date": "2026-10-08",
  "sources": [
   "https://arena.ai/leaderboard/chat/text"
  ],
  "uncertainty": "±6"
 },
 {
  "model": "anthropic-claude-fable-5-1",
  "benchmark": "lmarena-vision",
  "score": 1286,
  "unit": "Elo",
  "provenance": "independent",
  "setting": "max",
  "view": "Arena Vision overall, style control default, 165 models",
  "rank": 17,
  "rank_population": 165,
  "date": "2026-10-09",
  "sources": [
   "https://arena.ai/leaderboard/chat/vision"
  ],
  "uncertainty": "±10"
 },
 {
  "model": "anthropic-claude-fable-5-1",
  "benchmark": "mmmu",
  "score": 90.64,
  "unit": "%",
  "provenance": "independent",
  "setting": "Vals mirror",
  "view": "Vals.ai mirror shown on BenchLM",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://www.benchlm.ai/benchmarks/mmmu"
  ],
  "unverified": []
 },
 {
  "model": "anthropic-claude-fable-5-1",
  "benchmark": "osworld-2-0",
  "score": 80.7,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2026-09",
  "sources": [
   "https://vpsranking.com/news/ai/ai-2026-09-22-anthropic-claude-opus-5-5/"
  ]
 },
 {
  "model": "anthropic-claude-fable-5-1",
  "benchmark": "programbench",
  "score": 7,
  "unit": "%",
  "provenance": "independent",
  "setting": "Vals.ai, max effort",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://vals.ai/models/anthropic_claude-fable-5-1"
  ],
  "uncertainty": "±1.81"
 },
 {
  "model": "anthropic-claude-fable-5-1",
  "benchmark": "terminal-bench-2-1",
  "score": 85.02,
  "unit": "%",
  "provenance": "independent",
  "setting": "Vals.ai, max effort; 79.03% if fallback-assisted tasks count as failures",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://vals.ai/models/anthropic_claude-fable-5-1"
  ]
 },
 {
  "model": "anthropic-claude-fable-5-1",
  "benchmark": "terminal-bench-4-0",
  "score": 58.08,
  "unit": "%",
  "provenance": "independent",
  "setting": "Vals.ai, max effort",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://vals.ai/models/anthropic_claude-fable-5-1"
  ],
  "uncertainty": "±3.31"
 },
 {
  "model": "anthropic-claude-fable-5",
  "benchmark": "lmarena-text",
  "score": 1504,
  "unit": "Elo",
  "provenance": "independent",
  "setting": "high",
  "view": "Arena Text overall",
  "rank": 4,
  "rank_population": null,
  "date": "2026-10-08",
  "sources": [
   "https://arena.ai/leaderboard/chat/text"
  ],
  "uncertainty": "±4"
 },
 {
  "model": "anthropic-claude-fable-5",
  "benchmark": "lmarena-vision",
  "score": 1308,
  "unit": "Elo",
  "provenance": "independent",
  "setting": "high",
  "view": "Arena Vision overall, style control default, 165 models",
  "rank": 1,
  "rank_population": 165,
  "date": "2026-10-09",
  "sources": [
   "https://arena.ai/leaderboard/chat/vision"
  ],
  "uncertainty": "±7"
 },
 {
  "model": "anthropic-claude-fable-5",
  "benchmark": "swe-bench-pro",
  "score": 77.8,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://ecosistemastartup.com/claude-fable-5-93-9-en-swe-bench-y-lo-que-significa-para-founders/"
  ]
 },
 {
  "model": "anthropic-claude-fable-5",
  "benchmark": "swe-bench-pro",
  "score": 80,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "public board (per heyuan110)",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://www.heyuan110.com/posts/ai/2026-07-10-gpt-5-6-general-availability/"
  ]
 },
 {
  "model": "anthropic-claude-fable-5",
  "benchmark": "swe-bench-verified",
  "score": 93.9,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "secondary report; source flags possible Mythos attribution mix-up",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://ecosistemastartup.com/claude-fable-5-93-9-en-swe-bench-y-lo-que-significa-para-founders/"
  ]
 },
 {
  "model": "anthropic-claude-fable-5",
  "benchmark": "swe-bench-verified",
  "score": 95,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "5-trial average",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://leaderboard.steel.dev/leaderboards/swe-bench-verified.md"
  ]
 },
 {
  "model": "anthropic-claude-fable-5",
  "benchmark": "terminal-bench-2-0",
  "score": 82,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://ecosistemastartup.com/claude-fable-5-93-9-en-swe-bench-y-lo-que-significa-para-founders/"
  ]
 },
 {
  "model": "anthropic-claude-haiku-5-5",
  "benchmark": "aa-intelligence-index",
  "score": 43,
  "unit": "index",
  "provenance": "independent",
  "setting": "max",
  "view": "AA leaderboard, 205 current models",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://artificialanalysis.ai/leaderboards/models"
  ]
 },
 {
  "model": "anthropic-claude-mythos-5",
  "benchmark": "swe-bench-verified",
  "score": 95.5,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "max effort",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://leaderboard.steel.dev/leaderboards/swe-bench-verified.md"
  ]
 },
 {
  "model": "anthropic-claude-opus-4-1",
  "benchmark": "swe-bench-verified",
  "score": 74.5,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "No extended thinking; bash and string-replace file editor scaffold; full 500 problems",
  "view": "Anthropic announcement",
  "rank": null,
  "rank_population": null,
  "date": "2025-08-05",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://www.anthropic.com/news/claude-opus-4-1"
  ]
 },
 {
  "model": "anthropic-claude-opus-4-6",
  "benchmark": "lmarena-text",
  "score": 1504,
  "unit": "Elo",
  "provenance": "independent",
  "setting": "high",
  "view": "Arena Text overall",
  "rank": 3,
  "rank_population": null,
  "date": "2026-10-08",
  "sources": [
   "https://arena.ai/leaderboard/chat/text"
  ],
  "uncertainty": "±3"
 },
 {
  "model": "anthropic-claude-opus-4-6",
  "benchmark": "lmarena-vision",
  "score": 1299,
  "unit": "Elo",
  "provenance": "independent",
  "setting": "high",
  "view": "Arena Vision overall, style control default, 165 models",
  "rank": 3,
  "rank_population": 165,
  "date": "2026-10-09",
  "sources": [
   "https://arena.ai/leaderboard/chat/vision"
  ],
  "uncertainty": "±6"
 },
 {
  "model": "anthropic-claude-opus-4",
  "benchmark": "gpqa-diamond",
  "score": 74.9,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "Without extended thinking",
  "view": "Anthropic announcement",
  "rank": null,
  "rank_population": null,
  "date": "2025-05-22",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://www.anthropic.com/news/claude-4"
  ]
 },
 {
  "model": "anthropic-claude-opus-4",
  "benchmark": "mmmu",
  "score": 73.7,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "Without extended thinking",
  "view": "Anthropic announcement",
  "rank": null,
  "rank_population": null,
  "date": "2025-05-22",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://www.anthropic.com/news/claude-4"
  ]
 },
 {
  "model": "anthropic-claude-opus-4",
  "benchmark": "multilingual-mmlu",
  "score": 87.4,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "MMMLU, without extended thinking",
  "view": "Anthropic announcement",
  "rank": null,
  "rank_population": null,
  "date": "2025-05-22",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://www.anthropic.com/news/claude-4"
  ]
 },
 {
  "model": "anthropic-claude-opus-4",
  "benchmark": "swe-bench-verified",
  "score": 72.5,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "No extended thinking; bash and file editing tool scaffold",
  "view": "Anthropic announcement",
  "rank": null,
  "rank_population": null,
  "date": "2025-05-22",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://www.anthropic.com/news/claude-4"
  ]
 },
 {
  "model": "anthropic-claude-opus-5-5",
  "benchmark": "aa-intelligence-index",
  "score": 58,
  "unit": "index",
  "provenance": "independent",
  "setting": "max; 57.62 per secondary orcarouter",
  "view": "AA leaderboard, 205 current models",
  "rank": 1,
  "rank_population": 205,
  "date": "2026-10-10",
  "sources": [
   "https://artificialanalysis.ai/leaderboards/models"
  ]
 },
 {
  "model": "anthropic-claude-opus-5-5",
  "benchmark": "aa-intelligence-index",
  "score": 58,
  "unit": "index",
  "provenance": "independent",
  "setting": "max",
  "view": "AA model page, 227 models",
  "rank": 1,
  "rank_population": 227,
  "date": "2026-10-10",
  "sources": [
   "https://artificialanalysis.ai/models/claude-opus-5-5"
  ]
 },
 {
  "model": "anthropic-claude-opus-5-5",
  "benchmark": "arc-agi-2",
  "score": 93.3,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "high effort, $0.408/task",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://slash-digital.io/en/insights/ai-models-2026/"
  ]
 },
 {
  "model": "anthropic-claude-opus-5-5",
  "benchmark": "benchlm-composite",
  "score": 86.4,
  "unit": "index",
  "provenance": "vendor-reported",
  "setting": null,
  "view": "benchlm.ai frontier top 6",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-09",
  "sources": [
   "https://benchlm.ai/frontier-ai-models"
  ]
 },
 {
  "model": "anthropic-claude-opus-5-5",
  "benchmark": "cursorbench",
  "score": 57.8,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "CursorBench 4.0, max",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://llm-stats.com/blog/research/claude-opus-5-5-launch"
  ]
 },
 {
  "model": "anthropic-claude-opus-5-5",
  "benchmark": "epoch-capabilities-index",
  "score": 166.82,
  "unit": "index",
  "provenance": "maintainer-run",
  "setting": null,
  "view": "Epoch AI Benchmarking Hub",
  "rank": 1,
  "rank_population": null,
  "date": "2026-10-15",
  "sources": [
   "https://epoch.ai/data/eci_scores.csv",
   "https://epoch.ai/benchmarks"
  ],
  "unverified": [],
  "uncertainty": "CI 163.54 to 170.99"
 },
 {
  "model": "anthropic-claude-opus-5-5",
  "benchmark": "frontiercode-v1-1",
  "score": 54.4,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://llm-stats.com/blog/research/claude-opus-5-5-launch"
  ]
 },
 {
  "model": "anthropic-claude-opus-5-5",
  "benchmark": "gdpval-aa-v2-1",
  "score": 1846,
  "unit": "Elo",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://vpsranking.com/news/ai/ai-2026-09-22-anthropic-claude-opus-5-5/"
  ]
 },
 {
  "model": "anthropic-claude-opus-5-5",
  "benchmark": "humanitys-last-exam",
  "score": 61.4,
  "unit": "%",
  "provenance": "independent",
  "setting": "AA-measured",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://slash-digital.io/en/insights/ai-models-2026/"
  ]
 },
 {
  "model": "anthropic-claude-opus-5-5",
  "benchmark": "humanitys-last-exam",
  "score": 67.7,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "with tools (Anthropic)",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://slash-digital.io/en/insights/ai-models-2026/"
  ]
 },
 {
  "model": "anthropic-claude-opus-5-5",
  "benchmark": "lmarena-agent",
  "score": 14.33,
  "unit": "%",
  "provenance": "independent",
  "setting": "Claude Opus 5.5 (High)",
  "view": "Arena Agent overall",
  "rank": 1,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://arena.ai/leaderboard"
  ],
  "unverified": []
 },
 {
  "model": "anthropic-claude-opus-5-5",
  "benchmark": "lmarena-text",
  "score": 1507,
  "unit": "Elo",
  "provenance": "independent",
  "setting": "high",
  "view": "Arena Text overall",
  "rank": 2,
  "rank_population": null,
  "date": "2026-10-08",
  "sources": [
   "https://arena.ai/leaderboard/chat/text"
  ],
  "uncertainty": "±8"
 },
 {
  "model": "anthropic-claude-opus-5-5",
  "benchmark": "lmarena-vision",
  "score": 1293,
  "unit": "Elo",
  "provenance": "independent",
  "setting": "high",
  "view": "Arena Vision overall, style control default, 165 models",
  "rank": 11,
  "rank_population": 165,
  "date": "2026-10-09",
  "sources": [
   "https://arena.ai/leaderboard/chat/vision"
  ],
  "uncertainty": "±13"
 },
 {
  "model": "anthropic-claude-opus-5-5",
  "benchmark": "osworld-2-0",
  "score": 81.8,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "partial",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2026-09",
  "sources": [
   "https://vpsranking.com/news/ai/ai-2026-09-22-anthropic-claude-opus-5-5/"
  ]
 },
 {
  "model": "anthropic-claude-opus-5-5",
  "benchmark": "swe-bench-pro",
  "score": 89.9,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "Self-report",
  "view": "BenchLM aggregator, top score",
  "rank": 1,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://www.benchlm.ai/benchmarks/swePro"
  ],
  "unverified": []
 },
 {
  "model": "anthropic-claude-opus-5-5",
  "benchmark": "swe-bench-pro",
  "score": 89.9,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "system card",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://llm-stats.com/blog/research/claude-opus-5-5-launch"
  ]
 },
 {
  "model": "anthropic-claude-opus-5-5",
  "benchmark": "terminal-bench-4-0",
  "score": 64.8,
  "unit": "%",
  "provenance": "maintainer-run",
  "setting": "official board",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://slash-digital.io/en/insights/ai-models-2026/"
  ]
 },
 {
  "model": "anthropic-claude-opus-5-5",
  "benchmark": "terminal-bench-4-0",
  "score": 66.4,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "xhigh, with safeguards, SE about 2.6",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2026-09",
  "sources": [
   "https://vpsranking.com/news/ai/ai-2026-09-22-anthropic-claude-opus-5-5/",
   "https://slash-digital.io/en/insights/ai-models-2026/",
   "https://llm-stats.com/blog/research/claude-opus-5-5-launch"
  ]
 },
 {
  "model": "anthropic-claude-opus-5",
  "benchmark": "gdpval-aa-v2-1",
  "score": 1708,
  "unit": "Elo",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://vpsranking.com/news/ai/ai-2026-09-22-anthropic-claude-opus-5-5/"
  ]
 },
 {
  "model": "anthropic-claude-opus-5",
  "benchmark": "swe-bench-verified",
  "score": 96,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://leaderboard.steel.dev/leaderboards/swe-bench-verified.md"
  ]
 },
 {
  "model": "anthropic-claude-opus-5",
  "benchmark": "swe-bench-verified",
  "score": 96,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "Self-report; benchmark contaminated, display only",
  "view": "BenchLM aggregator, top score",
  "rank": 1,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://benchlm.ai/benchmarks/swe-bench-verified"
  ],
  "unverified": []
 },
 {
  "model": "anthropic-claude-opus-5",
  "benchmark": "swe-bench-verified",
  "score": 97,
  "unit": "%",
  "provenance": "independent",
  "setting": "Vals.ai, mini-swe-agent bash-only, +/-0.76",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://leaderboard.steel.dev/leaderboards/swe-bench-verified.md"
  ]
 },
 {
  "model": "anthropic-claude-opus-5",
  "benchmark": "terminal-bench-4-0",
  "score": 52.3,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://llm-stats.com/blog/research/claude-opus-5-5-launch"
  ]
 },
 {
  "model": "anthropic-claude-sonnet-4-5",
  "benchmark": "protocol-qa",
  "score": 0.83,
  "unit": "score",
  "provenance": "vendor-reported",
  "setting": "Human baseline 0.79",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2025-10-20",
  "sources": [
   "https://www.anthropic.com/news/claude-for-life-sciences"
  ]
 },
 {
  "model": "anthropic-claude-sonnet-5-5",
  "benchmark": "aa-intelligence-index",
  "score": 56,
  "unit": "index",
  "provenance": "independent",
  "setting": "max",
  "view": "AA leaderboard, 205 current models",
  "rank": 2,
  "rank_population": 205,
  "date": "2026-10-10",
  "sources": [
   "https://artificialanalysis.ai/leaderboards/models"
  ]
 },
 {
  "model": "anthropic-claude-sonnet-5-5",
  "benchmark": "benchlm-composite",
  "score": 83.9,
  "unit": "index",
  "provenance": "vendor-reported",
  "setting": null,
  "view": "benchlm.ai frontier top 6",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-09",
  "sources": [
   "https://benchlm.ai/frontier-ai-models"
  ]
 },
 {
  "model": "anthropic-claude-sonnet-5-5",
  "benchmark": "lmarena-text",
  "score": 1476,
  "unit": "Elo",
  "provenance": "independent",
  "setting": "xhigh",
  "view": "Arena Text overall",
  "rank": 32,
  "rank_population": null,
  "date": "2026-10-08",
  "sources": [
   "https://arena.ai/leaderboard/chat/text"
  ],
  "uncertainty": "±9"
 },
 {
  "model": "anthropic-claude-sonnet-5-5",
  "benchmark": "terminal-bench-4-0",
  "score": 61.8,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://slash-digital.io/en/insights/ai-models-2026/"
  ]
 },
 {
  "model": "anysphere-composer-2",
  "benchmark": "cursorbench",
  "score": 61.3,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://cursor.com/blog/composer-2"
  ]
 },
 {
  "model": "anysphere-composer-2",
  "benchmark": "swe-bench-multilingual",
  "score": 73.7,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://cursor.com/blog/composer-2"
  ]
 },
 {
  "model": "anysphere-composer-2",
  "benchmark": "terminal-bench-2-0",
  "score": 61.7,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://cursor.com/blog/composer-2"
  ]
 },
 {
  "model": "arcee-ai-trinity-large-thinking",
  "benchmark": "aime-2025",
  "score": 96.3,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": "Trinity-Large-Thinking model card",
  "rank": null,
  "rank_population": null,
  "date": "2026-04-01",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://huggingface.co/arcee-ai/Trinity-Large-Thinking"
  ]
 },
 {
  "model": "arcee-ai-trinity-large-thinking",
  "benchmark": "gpqa-diamond",
  "score": 76.3,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": "Trinity-Large-Thinking model card",
  "rank": null,
  "rank_population": null,
  "date": "2026-04-01",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://huggingface.co/arcee-ai/Trinity-Large-Thinking"
  ]
 },
 {
  "model": "arcee-ai-trinity-large-thinking",
  "benchmark": "ifbench",
  "score": 52.3,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": "Trinity-Large-Thinking model card",
  "rank": null,
  "rank_population": null,
  "date": "2026-04-01",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://huggingface.co/arcee-ai/Trinity-Large-Thinking"
  ]
 },
 {
  "model": "arcee-ai-trinity-large-thinking",
  "benchmark": "mmlu-pro",
  "score": 83.4,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": "Trinity-Large-Thinking model card",
  "rank": null,
  "rank_population": null,
  "date": "2026-04-01",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://huggingface.co/arcee-ai/Trinity-Large-Thinking"
  ]
 },
 {
  "model": "arcee-ai-trinity-large-thinking",
  "benchmark": "swe-bench-verified",
  "score": 63.2,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "Marked with an asterisk on the model card",
  "view": "Trinity-Large-Thinking model card",
  "rank": null,
  "rank_population": null,
  "date": "2026-04-01",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://huggingface.co/arcee-ai/Trinity-Large-Thinking"
  ]
 },
 {
  "model": "arcee-ai-trinity-large-thinking",
  "benchmark": "tau2-bench",
  "score": 94.7,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "Telecom domain",
  "view": "Trinity-Large-Thinking model card",
  "rank": null,
  "rank_population": null,
  "date": "2026-04-01",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://huggingface.co/arcee-ai/Trinity-Large-Thinking"
  ]
 },
 {
  "model": "archesweathergen",
  "benchmark": "weatherbench-2",
  "score": 130.1,
  "unit": "RMSE m2/s2",
  "provenance": "maintainer-run",
  "setting": "Z500 day 3, deterministic, ArchesWeatherGen (mean) vs ERA5",
  "view": "year 2020, 240x121 grid",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://researchsites.withgoogle.com/weatherbench/deterministic/"
  ]
 },
 {
  "model": "archesweathergen",
  "benchmark": "weatherbench-2",
  "score": 272.4,
  "unit": "RMSE m2/s2",
  "provenance": "maintainer-run",
  "setting": "Z500 day 5, deterministic, ArchesWeatherGen (mean) vs ERA5",
  "view": "year 2020, 240x121 grid",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://researchsites.withgoogle.com/weatherbench/deterministic/"
  ]
 },
 {
  "model": "archesweathergen",
  "benchmark": "weatherbench-2",
  "score": 41.9,
  "unit": "RMSE m2/s2",
  "provenance": "maintainer-run",
  "setting": "Z500 day 1, deterministic, ArchesWeatherGen (mean) vs ERA5",
  "view": "year 2020, 240x121 grid",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://researchsites.withgoogle.com/weatherbench/deterministic/"
  ]
 },
 {
  "model": "archesweathergen",
  "benchmark": "weatherbench-2",
  "score": 610.4,
  "unit": "RMSE m2/s2",
  "provenance": "maintainer-run",
  "setting": "Z500 day 10, deterministic, ArchesWeatherGen (mean) vs ERA5",
  "view": "year 2020, 240x121 grid",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://researchsites.withgoogle.com/weatherbench/deterministic/"
  ]
 },
 {
  "model": "artime",
  "benchmark": "nab",
  "score": 74.9,
  "unit": "NAB score",
  "provenance": "maintainer-run",
  "setting": "Standard profile, NAB v1.0 scoreboard",
  "view": null,
  "rank": 1,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://github.com/numenta/NAB"
  ]
 },
 {
  "model": "asymflux-2-klein",
  "benchmark": "geneval",
  "score": 0.82,
  "unit": "score",
  "provenance": "vendor-reported",
  "setting": "paper-reported, labelled unverified by Codesota; year 2026",
  "view": "Codesota aggregator",
  "rank": 7,
  "rank_population": 7,
  "date": "2026-05",
  "sources": [
   "https://arxiv.org/abs/2605.12964",
   "https://www.codesota.com/benchmark/geneval"
  ]
 },
 {
  "model": "auto-arima",
  "benchmark": "gift-eval",
  "score": 0.912,
  "unit": "CRPS (geo-mean, normalised to Seasonal Naive)",
  "provenance": "independent",
  "setting": "statistical; rank is average CRPS rank",
  "view": "Leaderboard rebuilt from the published raw results, 143 entries covering all 97 configurations",
  "rank": 131,
  "rank_population": 143,
  "date": "2026-10-09",
  "sources": [
   "https://huggingface.co/spaces/Salesforce/GIFT-Eval"
  ],
  "leakage": "no",
  "leakage_note": "Test Leak. column: No (Auto_Arima)"
 },
 {
  "model": "auto-arima",
  "benchmark": "gift-eval",
  "score": 1.074,
  "unit": "MASE (geo-mean, normalised to Seasonal Naive)",
  "provenance": "independent",
  "setting": "statistical",
  "view": "Leaderboard rebuilt from the published raw results, 143 entries covering all 97 configurations",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-09",
  "sources": [
   "https://huggingface.co/spaces/Salesforce/GIFT-Eval"
  ],
  "leakage": "no",
  "leakage_note": "Test Leak. column: No (Auto_Arima)"
 },
 {
  "model": "bagel-7b-mot",
  "benchmark": "geneval",
  "score": 0.88,
  "unit": "score",
  "provenance": "vendor-reported",
  "setting": "paper-reported, labelled unverified by Codesota; year 2025; with LLM rewriter",
  "view": "Codesota aggregator",
  "rank": 4,
  "rank_population": 7,
  "date": "2025-05",
  "sources": [
   "https://arxiv.org/abs/2505.14683",
   "https://www.codesota.com/benchmark/geneval"
  ]
 },
 {
  "model": "baguan",
  "benchmark": "weatherbench-2",
  "score": 127.8,
  "unit": "RMSE m2/s2",
  "provenance": "maintainer-run",
  "setting": "Z500 day 3, deterministic, Baguan vs ERA5",
  "view": "year 2020, 240x121 grid",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://researchsites.withgoogle.com/weatherbench/deterministic/"
  ]
 },
 {
  "model": "baguan",
  "benchmark": "weatherbench-2",
  "score": 273.5,
  "unit": "RMSE m2/s2",
  "provenance": "maintainer-run",
  "setting": "Z500 day 5, deterministic, Baguan vs ERA5",
  "view": "year 2020, 240x121 grid",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://researchsites.withgoogle.com/weatherbench/deterministic/"
  ]
 },
 {
  "model": "baguan",
  "benchmark": "weatherbench-2",
  "score": 41.5,
  "unit": "RMSE m2/s2",
  "provenance": "maintainer-run",
  "setting": "Z500 day 1, deterministic, Baguan vs ERA5",
  "view": "year 2020, 240x121 grid",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://researchsites.withgoogle.com/weatherbench/deterministic/"
  ]
 },
 {
  "model": "baguan",
  "benchmark": "weatherbench-2",
  "score": 625.8,
  "unit": "RMSE m2/s2",
  "provenance": "maintainer-run",
  "setting": "Z500 day 10, deterministic, Baguan vs ERA5",
  "view": "year 2020, 240x121 grid",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://researchsites.withgoogle.com/weatherbench/deterministic/"
  ]
 },
 {
  "model": "baichuan-ai-baichuan-m2-32b",
  "benchmark": "healthbench-consensus",
  "score": 91.5,
  "unit": "score",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2025-09",
  "sources": [
   "https://huggingface.co/baichuan-inc/Baichuan-M2-32B"
  ]
 },
 {
  "model": "baichuan-ai-baichuan-m2-32b",
  "benchmark": "healthbench-hard",
  "score": 34.7,
  "unit": "score",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2025-09",
  "sources": [
   "https://huggingface.co/baichuan-inc/Baichuan-M2-32B"
  ]
 },
 {
  "model": "baichuan-ai-baichuan-m2-32b",
  "benchmark": "healthbench",
  "score": 60.1,
  "unit": "score",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2025-09",
  "sources": [
   "https://huggingface.co/baichuan-inc/Baichuan-M2-32B"
  ]
 },
 {
  "model": "baidu-ernie-5-0-thinking-preview",
  "benchmark": "aa-intelligence-index",
  "score": 14,
  "unit": "index",
  "provenance": "independent",
  "setting": "asterisk on page",
  "view": "AA leaderboard, 205 current models",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://artificialanalysis.ai/leaderboards/models"
  ]
 },
 {
  "model": "baidu-ernie-5-1",
  "benchmark": "lmarena-text",
  "score": null,
  "unit": "Elo",
  "provenance": "independent",
  "setting": null,
  "view": "Arena Text overall",
  "rank": 49,
  "rank_population": null,
  "date": "2026-10-08",
  "sources": [
   "https://arena.ai/leaderboard/chat/text"
  ]
 },
 {
  "model": "baidu-paddleocr-vl-1-5",
  "benchmark": "omnidocbench-v1-6",
  "score": 94.93,
  "unit": "score",
  "provenance": "vendor-reported",
  "setting": "overall",
  "view": "PaddleOCR-VL-1.6 paper table",
  "rank": null,
  "rank_population": null,
  "date": "2026-06-02",
  "sources": [
   "https://arxiv.org/pdf/2606.03264"
  ]
 },
 {
  "model": "baidu-paddleocr-vl-1-5",
  "benchmark": "real5-omnidocbench",
  "score": 92.05,
  "unit": "score",
  "provenance": "vendor-reported",
  "setting": "overall",
  "view": "PaddleOCR-VL-1.6 paper table",
  "rank": null,
  "rank_population": null,
  "date": "2026-06-02",
  "sources": [
   "https://arxiv.org/pdf/2606.03264"
  ]
 },
 {
  "model": "baidu-paddleocr-vl-1-6",
  "benchmark": "omnidocbench-v1-6",
  "score": 96.33,
  "unit": "score",
  "provenance": "vendor-reported",
  "setting": "overall",
  "view": "PaddleOCR-VL-1.6 paper table",
  "rank": null,
  "rank_population": null,
  "date": "2026-06-02",
  "sources": [
   "https://arxiv.org/pdf/2606.03264"
  ]
 },
 {
  "model": "baidu-paddleocr-vl-1-6",
  "benchmark": "real5-omnidocbench",
  "score": 93.19,
  "unit": "score",
  "provenance": "vendor-reported",
  "setting": "overall",
  "view": "PaddleOCR-VL-1.6 paper table",
  "rank": null,
  "rank_population": null,
  "date": "2026-06-02",
  "sources": [
   "https://arxiv.org/pdf/2606.03264"
  ]
 },
 {
  "model": "bigcode-starcoder2-15b",
  "benchmark": "humaneval-plus",
  "score": 37.8,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/bigcode/starcoder2-15b"
  ]
 },
 {
  "model": "bigcode-starcoder2-15b",
  "benchmark": "humaneval",
  "score": 46.3,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/bigcode/starcoder2-15b"
  ]
 },
 {
  "model": "black-forest-labs-flux-2-dev",
  "benchmark": "aa-image-t2i-v2-0",
  "score": 1000,
  "unit": "Elo",
  "provenance": "independent",
  "setting": "approximate rank",
  "view": "AA Text-to-Image Arena, overall",
  "rank": 44,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://artificialanalysis.ai/text-to-image/arena/leaderboard-text"
  ]
 },
 {
  "model": "black-forest-labs-flux-2-klein-4b",
  "benchmark": "aa-image-t2i-v2-0",
  "score": 864,
  "unit": "Elo",
  "provenance": "independent",
  "setting": "approximate rank",
  "view": "AA Text-to-Image Arena, overall",
  "rank": 125,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://artificialanalysis.ai/text-to-image/arena/leaderboard-text"
  ]
 },
 {
  "model": "black-forest-labs-flux-2-klein-9b",
  "benchmark": "aa-image-t2i-v2-0",
  "score": 941,
  "unit": "Elo",
  "provenance": "independent",
  "setting": "approximate rank",
  "view": "AA Text-to-Image Arena, overall",
  "rank": 84,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://artificialanalysis.ai/text-to-image/arena/leaderboard-text"
  ]
 },
 {
  "model": "black-forest-labs-flux-2-max",
  "benchmark": "qwen-image-bench",
  "score": 55.33,
  "unit": "score",
  "provenance": "vendor-reported",
  "setting": "Qwen chart only; methodology unreleased",
  "view": "Qwen vendor chart",
  "rank": null,
  "rank_population": null,
  "date": "2026-09",
  "sources": [
   "https://datanorth.ai/news/qwen-releases-qwen-image-2-1"
  ]
 },
 {
  "model": "black-forest-labs-flux-3-image",
  "benchmark": "aa-image-t2i-v2-0",
  "score": 1115,
  "unit": "Elo",
  "provenance": "independent",
  "setting": "rank shown as 8-11",
  "view": "AA Text-to-Image Arena, overall",
  "rank": 8,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://artificialanalysis.ai/text-to-image/arena/leaderboard-text"
  ]
 },
 {
  "model": "black-forest-labs-flux-3-video",
  "benchmark": "aa-video-t2v",
  "score": 1128,
  "unit": "Elo",
  "provenance": "independent",
  "setting": "listed as FLUX 3",
  "view": "AA Text-to-Video leaderboard",
  "rank": 6,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://artificialanalysis.ai/video/leaderboard/text-to-video"
  ]
 },
 {
  "model": "black-forest-labs-flux-3-video",
  "benchmark": "lmarena-text-to-video",
  "score": 1493,
  "unit": "Elo",
  "provenance": "independent",
  "setting": "preliminary",
  "view": "LMArena Text-to-Video, updated 21 Sep 2026",
  "rank": 3,
  "rank_population": null,
  "date": "2026-09-21",
  "sources": [
   "https://arena.ai/leaderboard/text-to-video"
  ],
  "uncertainty": "±17"
 },
 {
  "model": "black-forest-labs-flux1-1-pro",
  "benchmark": "aa-image-arena",
  "score": 891,
  "unit": "Elo",
  "provenance": "independent",
  "setting": "text-to-image, 7,439 samples",
  "view": "AA text-to-image leaderboard, 168 models",
  "rank": 105,
  "rank_population": 168,
  "date": "2026-10-11",
  "uncertainty": "+/-7 (95% interval 884 to 898); rank range 103 to 111",
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://artificialanalysis.ai/image/leaderboard/text-to-image"
  ]
 },
 {
  "model": "blip3-o-8b",
  "benchmark": "geneval",
  "score": 0.84,
  "unit": "score",
  "provenance": "vendor-reported",
  "setting": "paper-reported, labelled unverified by Codesota; year 2025",
  "view": "Codesota aggregator",
  "rank": 6,
  "rank_population": 7,
  "date": "2025-05-14",
  "sources": [
   "https://arxiv.org/abs/2505.09568",
   "https://www.codesota.com/benchmark/geneval"
  ]
 },
 {
  "model": "blip3o-next-grpo-geneval-3b",
  "benchmark": "geneval",
  "score": 0.91,
  "unit": "score",
  "provenance": "vendor-reported",
  "setting": "paper-reported, labelled unverified by Codesota; year 2025",
  "view": "Codesota aggregator",
  "rank": 2,
  "rank_population": 7,
  "date": "2025-10-17",
  "sources": [
   "https://arxiv.org/abs/2510.15857",
   "https://www.codesota.com/benchmark/geneval"
  ]
 },
 {
  "model": "bloomberg-bloomberggpt",
  "benchmark": "convfinqa",
  "score": 43.41,
  "unit": "score",
  "provenance": "independent",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2023-05",
  "sources": [
   "https://arxiv.org/html/2305.05862v2"
  ]
 },
 {
  "model": "bloomberg-bloomberggpt",
  "benchmark": "fiqa-sentiment",
  "score": 75.07,
  "unit": "score",
  "provenance": "independent",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2023-05",
  "sources": [
   "https://arxiv.org/html/2305.05862v2"
  ]
 },
 {
  "model": "boltz-boltz-2",
  "benchmark": "fep-plus-openfe",
  "score": 0.62,
  "unit": "Pearson r",
  "provenance": "vendor-reported",
  "setting": "About 0.62; about 1,000x faster than FEP",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2025-06",
  "sources": [
   "https://intuitionlabs.ai/articles/open-source-ai-drug-discovery-boltz-pfizer",
   "https://github.com/jwohlwend/boltz"
  ]
 },
 {
  "model": "breezeblue-breeze-tts-2",
  "benchmark": "aa-tts",
  "score": 1222,
  "unit": "Elo",
  "provenance": "independent",
  "setting": null,
  "view": "AA Text-to-Speech arena, 96 models",
  "rank": 10,
  "rank_population": 96,
  "date": "2026-10-10",
  "sources": [
   "https://artificialanalysis.ai/text-to-speech/leaderboard"
  ]
 },
 {
  "model": "bytedance-bagel",
  "benchmark": "aa-image-t2i-v2-0",
  "score": 706,
  "unit": "Elo",
  "provenance": "independent",
  "setting": "Rank range 161 to 163",
  "view": "AA Text-to-Image Arena, 168 models",
  "rank": 162,
  "rank_population": 168,
  "date": "2026-10-11",
  "uncertainty": "95% CI 697 to 715 (+/-9)",
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://artificialanalysis.ai/image/leaderboard/text-to-image"
  ]
 },
 {
  "model": "bytedance-bagel",
  "benchmark": "mmmu",
  "score": 55.3,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": "BAGEL model card",
  "rank": null,
  "rank_population": null,
  "date": "2025-05",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://huggingface.co/ByteDance-Seed/BAGEL-7B-MoT"
  ]
 },
 {
  "model": "bytedance-dola-seed-2-0-pro",
  "benchmark": "lmarena-text",
  "score": null,
  "unit": "Elo",
  "provenance": "independent",
  "setting": null,
  "view": "Arena Text overall",
  "rank": 65,
  "rank_population": null,
  "date": "2026-10-08",
  "sources": [
   "https://arena.ai/leaderboard/chat/text"
  ]
 },
 {
  "model": "bytedance-doubao-seed-code",
  "benchmark": "aa-intelligence-index",
  "score": 17,
  "unit": "index",
  "provenance": "independent",
  "setting": "asterisk on page",
  "view": "AA leaderboard, 205 current models",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://artificialanalysis.ai/leaderboards/models"
  ]
 },
 {
  "model": "bytedance-seed-coder-8b-instruct",
  "benchmark": "humaneval",
  "score": 84.8,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/ByteDance-Seed/Seed-Coder-8B-Instruct"
  ]
 },
 {
  "model": "bytedance-seed-coder-8b-instruct",
  "benchmark": "livecodebench",
  "score": 24.7,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "LiveCodeBench 2410-2502",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/ByteDance-Seed/Seed-Coder-8B-Instruct"
  ]
 },
 {
  "model": "bytedance-seed-coder-8b-instruct",
  "benchmark": "mbpp",
  "score": 85.2,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/ByteDance-Seed/Seed-Coder-8B-Instruct"
  ]
 },
 {
  "model": "bytedance-seedance-1-0",
  "benchmark": "vbench-2-0",
  "score": 53.04,
  "unit": "%",
  "provenance": "maintainer-run",
  "setting": "Creativity score; Seedance 1.0 Pro",
  "view": "VBench-2.0",
  "rank": null,
  "rank_population": null,
  "date": "2025-06-26",
  "sources": [
   "https://huggingface.co/spaces/Vchitect/VBench_Leaderboard"
  ]
 },
 {
  "model": "bytedance-seedance-1-0",
  "benchmark": "vbench-2-0",
  "score": 59.81,
  "unit": "%",
  "provenance": "maintainer-run",
  "setting": "Total score; Seedance 1.0 Pro",
  "view": "VBench-2.0",
  "rank": 7,
  "rank_population": null,
  "date": "2025-06-26",
  "sources": [
   "https://huggingface.co/spaces/Vchitect/VBench_Leaderboard"
  ]
 },
 {
  "model": "bytedance-seedance-2-0",
  "benchmark": "aa-video-t2v",
  "score": 1116,
  "unit": "Elo",
  "provenance": "independent",
  "setting": "Dreamina Seedance 2.0",
  "view": "AA Text-to-Video leaderboard",
  "rank": 7,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://artificialanalysis.ai/video/leaderboard/text-to-video"
  ]
 },
 {
  "model": "bytedance-seedance-2-0",
  "benchmark": "lmarena-text-to-video",
  "score": 1479,
  "unit": "Elo",
  "provenance": "independent",
  "setting": "720p",
  "view": "LMArena Text-to-Video, updated 21 Sep 2026",
  "rank": 5,
  "rank_population": null,
  "date": "2026-09-21",
  "sources": [
   "https://arena.ai/leaderboard/text-to-video"
  ],
  "uncertainty": "±8"
 },
 {
  "model": "bytedance-seedance-2-5",
  "benchmark": "aa-video-t2v",
  "score": 1143,
  "unit": "Elo",
  "provenance": "independent",
  "setting": "Dreamina Seedance 2.5",
  "view": "AA Text-to-Video leaderboard",
  "rank": 3,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://artificialanalysis.ai/video/leaderboard/text-to-video"
  ]
 },
 {
  "model": "bytedance-seedance-2-5",
  "benchmark": "lmarena-text-to-video",
  "score": 1474,
  "unit": "Elo",
  "provenance": "independent",
  "setting": "720p",
  "view": "LMArena Text-to-Video, updated 21 Sep 2026",
  "rank": 7,
  "rank_population": null,
  "date": "2026-09-21",
  "sources": [
   "https://arena.ai/leaderboard/text-to-video"
  ],
  "uncertainty": "±9"
 },
 {
  "model": "bytedance-seedream-4-0",
  "benchmark": "aa-image-t2i-v2-0",
  "score": 1030,
  "unit": "Elo",
  "provenance": "independent",
  "setting": "rank shown as 20-27",
  "view": "AA Text-to-Image Arena, overall",
  "rank": 20,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://artificialanalysis.ai/text-to-image/arena/leaderboard-text"
  ]
 },
 {
  "model": "bytedance-seedream-4-5",
  "benchmark": "aa-image-t2i-v2-0",
  "score": 1023,
  "unit": "Elo",
  "provenance": "independent",
  "setting": null,
  "view": "AA Text-to-Image leaderboard, overall",
  "rank": 27,
  "rank_population": null,
  "date": "2026-10-11",
  "uncertainty": "+-9; 95% interval 1014 to 1032",
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://artificialanalysis.ai/image/leaderboard/text-to-image"
  ]
 },
 {
  "model": "bytedance-seedream-5-0-pro",
  "benchmark": "aa-image-t2i-v2-0",
  "score": 1080,
  "unit": "Elo",
  "provenance": "independent",
  "setting": "rank shown as 17-18",
  "view": "AA Text-to-Image Arena, overall",
  "rank": 17,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://artificialanalysis.ai/text-to-image/arena/leaderboard-text"
  ]
 },
 {
  "model": "bytedance-seedream-5-0-pro",
  "benchmark": "lmarena-text-to-image",
  "score": 1255,
  "unit": "Elo",
  "provenance": "independent",
  "setting": null,
  "view": "LMArena Text-to-Image, overall, updated 7 Oct 2026",
  "rank": 12,
  "rank_population": null,
  "date": "2026-10-07",
  "sources": [
   "https://arena.ai/leaderboard/text-to-image"
  ],
  "uncertainty": "±4"
 },
 {
  "model": "cad-ose",
  "benchmark": "nab",
  "score": 69.9,
  "unit": "NAB score",
  "provenance": "maintainer-run",
  "setting": "Standard profile",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://github.com/numenta/NAB"
  ]
 },
 {
  "model": "carnegie-mellon-university-moment-1-large",
  "benchmark": "tsb-ad",
  "score": 0.39,
  "unit": "VUS-PR",
  "provenance": "independent",
  "setting": "Univariate, fine-tuned (FT); as reported in the PaAno paper",
  "view": null,
  "rank": 5,
  "rank_population": null,
  "date": "2026-07-01",
  "sources": [
   "https://arxiv.org/pdf/2602.01359"
  ]
 },
 {
  "model": "cartesia-sonic-3-6",
  "benchmark": "aa-tts",
  "score": 1284,
  "unit": "Elo",
  "provenance": "independent",
  "setting": null,
  "view": "AA Text-to-Speech arena, 96 models",
  "rank": 4,
  "rank_population": 96,
  "date": "2026-10-10",
  "sources": [
   "https://artificialanalysis.ai/text-to-speech/leaderboard"
  ]
 },
 {
  "model": "cognition-swe-2",
  "benchmark": "deepswe-v1-1",
  "score": 73,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://www.orcarouter.ai/fr/blog/swe-2"
  ]
 },
 {
  "model": "cognition-swe-2",
  "benchmark": "frontiercode-v1-1",
  "score": 50,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://www.orcarouter.ai/fr/blog/swe-2"
  ]
 },
 {
  "model": "cognition-swe-2",
  "benchmark": "terminal-bench-2-1",
  "score": 92.8,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://www.orcarouter.ai/fr/blog/swe-2"
  ]
 },
 {
  "model": "cognition-swe-2",
  "benchmark": "terminal-bench-4-0",
  "score": 27.3,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://www.orcarouter.ai/fr/blog/swe-2"
  ]
 },
 {
  "model": "cogvideox-i2v",
  "benchmark": "worldscore",
  "score": 59.12,
  "unit": "score",
  "provenance": "maintainer-run",
  "setting": "Dynamic aggregate",
  "view": "WorldScore paper table",
  "rank": null,
  "rank_population": null,
  "date": "2025",
  "sources": [
   "https://arxiv.org/html/2504.00983v2"
  ]
 },
 {
  "model": "cogvideox-i2v",
  "benchmark": "worldscore",
  "score": 62.15,
  "unit": "score",
  "provenance": "maintainer-run",
  "setting": "Static aggregate",
  "view": "WorldScore paper table",
  "rank": null,
  "rank_population": null,
  "date": "2025",
  "sources": [
   "https://arxiv.org/html/2504.00983v2"
  ]
 },
 {
  "model": "cohere-command-a-03-2025",
  "benchmark": "lmarena-text",
  "score": null,
  "unit": "Elo",
  "provenance": "independent",
  "setting": null,
  "view": "Arena Text overall",
  "rank": 210,
  "rank_population": null,
  "date": "2026-10-08",
  "sources": [
   "https://arena.ai/leaderboard/chat/text"
  ]
 },
 {
  "model": "cohere-command-a-plus",
  "benchmark": "aa-intelligence-index",
  "score": 13,
  "unit": "index",
  "provenance": "independent",
  "setting": null,
  "view": "AA leaderboard, 205 current models",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://artificialanalysis.ai/leaderboards/models"
  ]
 },
 {
  "model": "cohere-command-r-mar-24",
  "benchmark": "mmlu-pro",
  "score": 37.9,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "TIGER-Lab MMLU-Pro as quoted on the model card",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://huggingface.co/CohereLabs/c4ai-command-r-v01"
  ]
 },
 {
  "model": "cohere-command-r-plus-apr-24",
  "benchmark": "arc-c",
  "score": 70.99,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "Open LLM Leaderboard figures as quoted on the model card",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2024-04",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://huggingface.co/CohereLabs/c4ai-command-r-plus"
  ]
 },
 {
  "model": "cohere-command-r-plus-apr-24",
  "benchmark": "gsm8k",
  "score": 70.7,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "Open LLM Leaderboard figures as quoted on the model card",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2024-04",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://huggingface.co/CohereLabs/c4ai-command-r-plus"
  ]
 },
 {
  "model": "cohere-command-r-plus-apr-24",
  "benchmark": "hellaswag",
  "score": 88.6,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "Open LLM Leaderboard figures as quoted on the model card",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2024-04",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://huggingface.co/CohereLabs/c4ai-command-r-plus"
  ]
 },
 {
  "model": "cohere-command-r-plus-apr-24",
  "benchmark": "mmlu",
  "score": 75.7,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "Open LLM Leaderboard figures as quoted on the model card",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2024-04",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://huggingface.co/CohereLabs/c4ai-command-r-plus"
  ]
 },
 {
  "model": "cohere-labs-tiny-aya-global",
  "benchmark": "gpqa-diamond",
  "score": 28.28,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/CohereLabs/tiny-aya-global"
  ]
 },
 {
  "model": "cohere-labs-tiny-aya-global",
  "benchmark": "sea-helm",
  "score": 19.19,
  "unit": "score",
  "provenance": "maintainer-run",
  "setting": "Checkpoint tiny-aya-global as listed; release view (data last updated 18 Sep 2026); score is the average of 2000 bootstraps",
  "view": "SEA-HELM leaderboard, 58 models, SEA average",
  "rank": null,
  "rank_population": null,
  "date": "2026-09-18",
  "uncertainty": "95% CI [-0.40, +0.41]",
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://leaderboard.sea-lion.ai/detailed/SEA"
  ]
 },
 {
  "model": "cohere-labs-tiny-aya-global",
  "benchmark": "sea-helm",
  "score": 32.12,
  "unit": "score",
  "provenance": "maintainer-run",
  "setting": "Checkpoint tiny-aya-global as listed; release view (data last updated 18 Sep 2026); score is the average of 2000 bootstraps",
  "view": "SEA-HELM leaderboard, 58 models, Indonesian (ID)",
  "rank": null,
  "rank_population": null,
  "date": "2026-09-18",
  "uncertainty": "95% CI [-1.13, +1.13]",
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://leaderboard.sea-lion.ai/detailed/ID"
  ]
 },
 {
  "model": "cohere-labs-tiny-aya-water",
  "benchmark": "sea-helm",
  "score": 19.75,
  "unit": "score",
  "provenance": "maintainer-run",
  "setting": "Checkpoint tiny-aya-water as listed; release view (data last updated 18 Sep 2026); score is the average of 2000 bootstraps",
  "view": "SEA-HELM leaderboard, 58 models, SEA average",
  "rank": null,
  "rank_population": null,
  "date": "2026-09-18",
  "uncertainty": "95% CI [-0.40, +0.43]",
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://leaderboard.sea-lion.ai/detailed/SEA"
  ]
 },
 {
  "model": "cohere-labs-tiny-aya-water",
  "benchmark": "sea-helm",
  "score": 33.23,
  "unit": "score",
  "provenance": "maintainer-run",
  "setting": "Checkpoint tiny-aya-water as listed; release view (data last updated 18 Sep 2026); score is the average of 2000 bootstraps",
  "view": "SEA-HELM leaderboard, 58 models, Indonesian (ID)",
  "rank": null,
  "rank_population": null,
  "date": "2026-09-18",
  "uncertainty": "95% CI [-1.13, +1.13]",
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://leaderboard.sea-lion.ai/detailed/ID"
  ]
 },
 {
  "model": "cohere-transcribe",
  "benchmark": "librispeech",
  "score": 1.25,
  "unit": "WER",
  "provenance": "vendor-reported",
  "setting": "test-clean",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2026-03",
  "sources": [
   "https://select.keenable.ai/r/speech-recognition-accuracy-leaders-2022-2026/JbURQjlVooLQ6J10NkbRVw"
  ]
 },
 {
  "model": "cohere-transcribe",
  "benchmark": "librispeech",
  "score": 2.37,
  "unit": "WER",
  "provenance": "vendor-reported",
  "setting": "test-other",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2026-03",
  "sources": [
   "https://select.keenable.ai/r/speech-recognition-accuracy-leaders-2022-2026/JbURQjlVooLQ6J10NkbRVw"
  ]
 },
 {
  "model": "cohere-transcribe",
  "benchmark": "open-asr-leaderboard",
  "score": 5.42,
  "unit": "WER",
  "provenance": "maintainer-run",
  "setting": "eight-set macro-average English WER",
  "view": "snapshot 2026-05-06 via benchmarklist",
  "rank": 2,
  "rank_population": null,
  "date": "2026-05-06",
  "sources": [
   "https://benchmarklist.com/benchmarks/open_asr_leaderboard/"
  ]
 },
 {
  "model": "conv-ae",
  "benchmark": "skab",
  "score": 0.78,
  "unit": "F1",
  "provenance": "maintainer-run",
  "setting": "Outlier detection leaderboard",
  "view": null,
  "rank": 1,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://github.com/waico/SKAB"
  ]
 },
 {
  "model": "ctranspath",
  "benchmark": "virchow-pan-cancer-detection",
  "score": 0.907,
  "unit": "AUROC",
  "provenance": "vendor-reported",
  "setting": "As reported in the Virchow paper",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2024-07-22",
  "sources": [
   "https://www.nature.com/articles/s41591-024-03141-0"
  ]
 },
 {
  "model": "databricks-dbrx",
  "benchmark": "arc-c",
  "score": 68.9,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "DBRX Instruct; 25-shot",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2024-03-27",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://www.databricks.com/blog/introducing-dbrx-new-state-art-open-llm"
  ]
 },
 {
  "model": "databricks-dbrx",
  "benchmark": "gsm8k",
  "score": 66.9,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "DBRX Instruct; 5-shot maj@13 (Table 1)",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2024-03-27",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://www.databricks.com/blog/introducing-dbrx-new-state-art-open-llm"
  ]
 },
 {
  "model": "databricks-dbrx",
  "benchmark": "gsm8k",
  "score": 72.8,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "DBRX Instruct; 5-shot, newer harness commit (Table 2)",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2024-03-27",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://www.databricks.com/blog/introducing-dbrx-new-state-art-open-llm"
  ]
 },
 {
  "model": "databricks-dbrx",
  "benchmark": "hellaswag",
  "score": 89,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "DBRX Instruct; 10-shot",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2024-03-27",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://www.databricks.com/blog/introducing-dbrx-new-state-art-open-llm"
  ]
 },
 {
  "model": "databricks-dbrx",
  "benchmark": "humaneval",
  "score": 70.1,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "DBRX Instruct; 0-shot pass@1",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2024-03-27",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://www.databricks.com/blog/introducing-dbrx-new-state-art-open-llm"
  ]
 },
 {
  "model": "databricks-dbrx",
  "benchmark": "mmlu",
  "score": 73.7,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "DBRX Instruct; 5-shot",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2024-03-27",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://www.databricks.com/blog/introducing-dbrx-new-state-art-open-llm"
  ]
 },
 {
  "model": "datadog-toto-2-0-1b",
  "benchmark": "gift-eval",
  "score": 21.1,
  "unit": "mean CRPS rank",
  "provenance": "vendor-reported",
  "setting": "zero-shot foundation-model CRPS rank, lower is better",
  "view": "Toto 2.0 report (Datadog)",
  "rank": null,
  "rank_population": null,
  "date": "2026-06",
  "sources": [
   "https://arxiv.org/pdf/2605.20119"
  ]
 },
 {
  "model": "datadog-toto-2-0-2-5b",
  "benchmark": "gift-eval",
  "score": 0.476,
  "unit": "CRPS (geo-mean, normalised to Seasonal Naive)",
  "provenance": "independent",
  "setting": "pretrained; rank is average CRPS rank",
  "view": "Leaderboard rebuilt from the published raw results, 143 entries covering all 97 configurations",
  "rank": 50,
  "rank_population": 143,
  "date": "2026-10-09",
  "sources": [
   "https://huggingface.co/spaces/Salesforce/GIFT-Eval"
  ],
  "leakage": "no",
  "leakage_note": "Test Leak. column: No (Toto-2.0-2.5B (code))"
 },
 {
  "model": "datadog-toto-2-0-2-5b",
  "benchmark": "gift-eval",
  "score": 0.696,
  "unit": "MASE (geo-mean, normalised to Seasonal Naive)",
  "provenance": "independent",
  "setting": "pretrained",
  "view": "Leaderboard rebuilt from the published raw results, 143 entries covering all 97 configurations",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-09",
  "sources": [
   "https://huggingface.co/spaces/Salesforce/GIFT-Eval"
  ],
  "leakage": "no",
  "leakage_note": "Test Leak. column: No (Toto-2.0-2.5B (code))"
 },
 {
  "model": "datadog-toto-2-0-2-5b",
  "benchmark": "gift-eval",
  "score": 20.3,
  "unit": "mean CRPS rank",
  "provenance": "vendor-reported",
  "setting": "zero-shot foundation-model CRPS rank, lower is better",
  "view": "Toto 2.0 report (Datadog)",
  "rank": null,
  "rank_population": null,
  "date": "2026-06",
  "sources": [
   "https://arxiv.org/pdf/2605.20119"
  ]
 },
 {
  "model": "datadog-toto-2-0-313m",
  "benchmark": "gift-eval",
  "score": 21.4,
  "unit": "mean CRPS rank",
  "provenance": "vendor-reported",
  "setting": "zero-shot foundation-model CRPS rank, lower is better",
  "view": "Toto 2.0 report (Datadog)",
  "rank": null,
  "rank_population": null,
  "date": "2026-06",
  "sources": [
   "https://arxiv.org/pdf/2605.20119"
  ]
 },
 {
  "model": "deepant",
  "benchmark": "tsb-ad",
  "score": 0.31,
  "unit": "VUS-PR",
  "provenance": "independent",
  "setting": "Multivariate; tie with PCA; PaAno paper",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2026-07-01",
  "sources": [
   "https://arxiv.org/pdf/2602.01359"
  ]
 },
 {
  "model": "deepseek-deepseek-ocr-2",
  "benchmark": "omnidocbench-v1-6",
  "score": 90.25,
  "unit": "score",
  "provenance": "vendor-reported",
  "setting": "overall",
  "view": "PaddleOCR-VL-1.6 paper table",
  "rank": null,
  "rank_population": null,
  "date": "2026-06-02",
  "sources": [
   "https://arxiv.org/pdf/2606.03264"
  ]
 },
 {
  "model": "deepseek-deepseek-ocr-2",
  "benchmark": "real5-omnidocbench",
  "score": 73.01,
  "unit": "score",
  "provenance": "vendor-reported",
  "setting": "overall",
  "view": "PaddleOCR-VL-1.6 paper table",
  "rank": null,
  "rank_population": null,
  "date": "2026-06-02",
  "sources": [
   "https://arxiv.org/pdf/2606.03264"
  ]
 },
 {
  "model": "deepseek-deepseek-ocr",
  "benchmark": "real5-omnidocbench",
  "score": 73.99,
  "unit": "score",
  "provenance": "vendor-reported",
  "setting": "overall",
  "view": "PaddleOCR-VL-1.6 paper table",
  "rank": null,
  "rank_population": null,
  "date": "2026-06-02",
  "sources": [
   "https://arxiv.org/pdf/2606.03264"
  ]
 },
 {
  "model": "deepseek-deepseek-v2-5-1210",
  "benchmark": "livecodebench",
  "score": 34.38,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "2024-08-01 to 2024-12-01 window; up from 29.2",
  "view": "DeepSeek-V2.5-1210 model card",
  "rank": null,
  "rank_population": null,
  "date": "2024-12",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://huggingface.co/deepseek-ai/DeepSeek-V2.5-1210"
  ]
 },
 {
  "model": "deepseek-deepseek-v2-5-1210",
  "benchmark": "math-500",
  "score": 82.8,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "Up from 74.8 for DeepSeek-V2.5",
  "view": "DeepSeek-V2.5-1210 model card",
  "rank": null,
  "rank_population": null,
  "date": "2024-12",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://huggingface.co/deepseek-ai/DeepSeek-V2.5-1210"
  ]
 },
 {
  "model": "deepseek-deepseek-v3-1-terminus",
  "benchmark": "browsecomp",
  "score": 38.5,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "Model card comparison table; mode not stated",
  "view": "DeepSeek-V3.1-Terminus model card",
  "rank": null,
  "rank_population": null,
  "date": "2025-09-22",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://huggingface.co/deepseek-ai/DeepSeek-V3.1-Terminus"
  ]
 },
 {
  "model": "deepseek-deepseek-v3-1-terminus",
  "benchmark": "gpqa-diamond",
  "score": 80.7,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "Model card comparison table; mode not stated",
  "view": "DeepSeek-V3.1-Terminus model card",
  "rank": null,
  "rank_population": null,
  "date": "2025-09-22",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://huggingface.co/deepseek-ai/DeepSeek-V3.1-Terminus"
  ]
 },
 {
  "model": "deepseek-deepseek-v3-1-terminus",
  "benchmark": "livecodebench",
  "score": 74.9,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "Model card comparison table; mode not stated",
  "view": "DeepSeek-V3.1-Terminus model card",
  "rank": null,
  "rank_population": null,
  "date": "2025-09-22",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://huggingface.co/deepseek-ai/DeepSeek-V3.1-Terminus"
  ]
 },
 {
  "model": "deepseek-deepseek-v3-1-terminus",
  "benchmark": "mmlu-pro",
  "score": 85,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "Model card comparison table; mode not stated",
  "view": "DeepSeek-V3.1-Terminus model card",
  "rank": null,
  "rank_population": null,
  "date": "2025-09-22",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://huggingface.co/deepseek-ai/DeepSeek-V3.1-Terminus"
  ]
 },
 {
  "model": "deepseek-deepseek-v3-1-terminus",
  "benchmark": "swe-bench-multilingual",
  "score": 57.8,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "Model card comparison table; mode not stated",
  "view": "DeepSeek-V3.1-Terminus model card",
  "rank": null,
  "rank_population": null,
  "date": "2025-09-22",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://huggingface.co/deepseek-ai/DeepSeek-V3.1-Terminus"
  ]
 },
 {
  "model": "deepseek-deepseek-v3-1-terminus",
  "benchmark": "swe-bench-verified",
  "score": 68.4,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "Model card comparison table; mode not stated",
  "view": "DeepSeek-V3.1-Terminus model card",
  "rank": null,
  "rank_population": null,
  "date": "2025-09-22",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://huggingface.co/deepseek-ai/DeepSeek-V3.1-Terminus"
  ]
 },
 {
  "model": "deepseek-deepseek-v3-1",
  "benchmark": "aime-2025",
  "score": 88.4,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "Thinking mode, Pass@1",
  "view": "DeepSeek-V3.1 model card",
  "rank": null,
  "rank_population": null,
  "date": "2025-08-21",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://huggingface.co/deepseek-ai/DeepSeek-V3.1"
  ]
 },
 {
  "model": "deepseek-deepseek-v3-1",
  "benchmark": "browsecomp",
  "score": 30,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "Thinking mode, internal search agent framework",
  "view": "DeepSeek-V3.1 model card",
  "rank": null,
  "rank_population": null,
  "date": "2025-08-21",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://huggingface.co/deepseek-ai/DeepSeek-V3.1"
  ]
 },
 {
  "model": "deepseek-deepseek-v3-1",
  "benchmark": "gpqa-diamond",
  "score": 80.1,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "Thinking mode, Pass@1",
  "view": "DeepSeek-V3.1 model card",
  "rank": null,
  "rank_population": null,
  "date": "2025-08-21",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://huggingface.co/deepseek-ai/DeepSeek-V3.1"
  ]
 },
 {
  "model": "deepseek-deepseek-v3-1",
  "benchmark": "livecodebench",
  "score": 74.8,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "Thinking mode, 2408 to 2505, Pass@1",
  "view": "DeepSeek-V3.1 model card",
  "rank": null,
  "rank_population": null,
  "date": "2025-08-21",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://huggingface.co/deepseek-ai/DeepSeek-V3.1"
  ]
 },
 {
  "model": "deepseek-deepseek-v3-1",
  "benchmark": "mmlu-pro",
  "score": 84.8,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "Thinking mode, EM",
  "view": "DeepSeek-V3.1 model card",
  "rank": null,
  "rank_population": null,
  "date": "2025-08-21",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://huggingface.co/deepseek-ai/DeepSeek-V3.1"
  ]
 },
 {
  "model": "deepseek-deepseek-v3-1",
  "benchmark": "swe-bench-multilingual",
  "score": 54.5,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "Non-thinking, agent mode",
  "view": "DeepSeek-V3.1 model card",
  "rank": null,
  "rank_population": null,
  "date": "2025-08-21",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://huggingface.co/deepseek-ai/DeepSeek-V3.1"
  ]
 },
 {
  "model": "deepseek-deepseek-v3-1",
  "benchmark": "swe-bench-verified",
  "score": 66,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "Non-thinking, agent mode",
  "view": "DeepSeek-V3.1 model card",
  "rank": null,
  "rank_population": null,
  "date": "2025-08-21",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://huggingface.co/deepseek-ai/DeepSeek-V3.1"
  ]
 },
 {
  "model": "deepseek-deepseek-v4-1-flash",
  "benchmark": "aa-intelligence-index",
  "score": 39,
  "unit": "index",
  "provenance": "independent",
  "setting": "max",
  "view": "AA leaderboard, 205 current models",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://artificialanalysis.ai/leaderboards/models"
  ]
 },
 {
  "model": "deepseek-deepseek-v4-1-flash",
  "benchmark": "codeforces",
  "score": 3471,
  "unit": "rating",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash"
  ]
 },
 {
  "model": "deepseek-deepseek-v4-1-flash",
  "benchmark": "deepswe-v1-1",
  "score": 74.2,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "mini-SWE",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash"
  ]
 },
 {
  "model": "deepseek-deepseek-v4-1-flash",
  "benchmark": "gpqa-diamond",
  "score": 90.9,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash"
  ]
 },
 {
  "model": "deepseek-deepseek-v4-1-flash",
  "benchmark": "lmarena-text",
  "score": 1475,
  "unit": "Elo",
  "provenance": "independent",
  "setting": "deepseek-v4.1-flash-max",
  "view": "Arena Text overall",
  "rank": 39,
  "rank_population": null,
  "date": "2026-10-08",
  "sources": [
   "https://arena.ai/leaderboard/chat/text"
  ],
  "uncertainty": "±7"
 },
 {
  "model": "deepseek-deepseek-v4-1-flash",
  "benchmark": "terminal-bench-2-1",
  "score": 90.6,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash"
  ]
 },
 {
  "model": "deepseek-deepseek-v4-1-flash",
  "benchmark": "terminal-bench-2-1",
  "score": 90.6,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "DeepSeek Harness Minimal",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash"
  ]
 },
 {
  "model": "deepseek-deepseek-v4-1-flash",
  "benchmark": "terminal-bench-3-0",
  "score": 30,
  "unit": null,
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash"
  ]
 },
 {
  "model": "deepseek-deepseek-v4-1-flash",
  "benchmark": "terminal-bench-4-0",
  "score": 31.2,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash"
  ]
 },
 {
  "model": "deepseek-deepseek-v4-flash",
  "benchmark": "gpqa-diamond",
  "score": 89.9,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/deepseek-ai"
  ]
 },
 {
  "model": "deepseek-deepseek-v4-flash",
  "benchmark": "livecodebench",
  "score": 91.6,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://blog.buildfastwithai.com/deepseek-v4-pro-review-2026",
   "https://leaderboard.steel.dev/leaderboards/swe-bench-verified.md"
  ]
 },
 {
  "model": "deepseek-deepseek-v4-flash",
  "benchmark": "swe-bench-verified",
  "score": 79,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://blog.buildfastwithai.com/deepseek-v4-pro-review-2026",
   "https://leaderboard.steel.dev/leaderboards/swe-bench-verified.md"
  ]
 },
 {
  "model": "deepseek-deepseek-v4-flash",
  "benchmark": "terminal-bench-2-0",
  "score": 56.9,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://blog.buildfastwithai.com/deepseek-v4-pro-review-2026",
   "https://leaderboard.steel.dev/leaderboards/swe-bench-verified.md"
  ]
 },
 {
  "model": "deepseek-deepseek-v4-pro-0813",
  "benchmark": "lmarena-text",
  "score": 1465,
  "unit": "Elo",
  "provenance": "independent",
  "setting": "deepseek-v4-pro-high-20260813",
  "view": "Arena Text overall",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-08",
  "sources": [
   "https://arena.ai/leaderboard/chat/text"
  ],
  "uncertainty": "±7"
 },
 {
  "model": "deepseek-deepseek-v4-pro",
  "benchmark": "codeforces",
  "score": 3206,
  "unit": "rating",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://blog.buildfastwithai.com/deepseek-v4-pro-review-2026",
   "https://leaderboard.steel.dev/leaderboards/swe-bench-verified.md"
  ]
 },
 {
  "model": "deepseek-deepseek-v4-pro",
  "benchmark": "gpqa-diamond",
  "score": 90.1,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro"
  ]
 },
 {
  "model": "deepseek-deepseek-v4-pro",
  "benchmark": "hle",
  "score": 37.7,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro"
  ]
 },
 {
  "model": "deepseek-deepseek-v4-pro",
  "benchmark": "livecodebench",
  "score": 93.5,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://blog.buildfastwithai.com/deepseek-v4-pro-review-2026",
   "https://leaderboard.steel.dev/leaderboards/swe-bench-verified.md",
   "https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro"
  ]
 },
 {
  "model": "deepseek-deepseek-v4-pro",
  "benchmark": "mmlu-pro",
  "score": 87.5,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro"
  ]
 },
 {
  "model": "deepseek-deepseek-v4-pro",
  "benchmark": "swe-bench-verified",
  "score": 80.6,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://blog.buildfastwithai.com/deepseek-v4-pro-review-2026",
   "https://leaderboard.steel.dev/leaderboards/swe-bench-verified.md",
   "https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro"
  ]
 },
 {
  "model": "deepseek-deepseek-v4-pro",
  "benchmark": "terminal-bench-2-0",
  "score": 67.9,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://blog.buildfastwithai.com/deepseek-v4-pro-review-2026",
   "https://leaderboard.steel.dev/leaderboards/swe-bench-verified.md"
  ]
 },
 {
  "model": "dmlc-xgboost",
  "benchmark": "tabarena",
  "score": 1214,
  "unit": "Elo",
  "provenance": "maintainer-run",
  "setting": "default",
  "view": "All Tasks, no imputation, snapshot 2026-05-06, 59 entries",
  "rank": 33,
  "rank_population": 59,
  "date": "2026-05-06",
  "sources": [
   "https://benchmarklist.com/benchmarks/tabarena_all/"
  ]
 },
 {
  "model": "dmlc-xgboost",
  "benchmark": "tabarena",
  "score": 1352,
  "unit": "Elo",
  "provenance": "maintainer-run",
  "setting": "tuned",
  "view": "All Tasks, no imputation, snapshot 2026-05-06, 59 entries",
  "rank": 22,
  "rank_population": 59,
  "date": "2026-05-06",
  "sources": [
   "https://benchmarklist.com/benchmarks/tabarena_all/"
  ]
 },
 {
  "model": "dmlc-xgboost",
  "benchmark": "tabarena",
  "score": 1376,
  "unit": "Elo",
  "provenance": "maintainer-run",
  "setting": "tuned + ensembled",
  "view": "All Tasks, no imputation, snapshot 2026-05-06, 59 entries",
  "rank": 19,
  "rank_population": 59,
  "date": "2026-05-06",
  "sources": [
   "https://benchmarklist.com/benchmarks/tabarena_all/"
  ]
 },
 {
  "model": "ecmwf-ifs-ens",
  "benchmark": "weatherbench-2",
  "score": 1.603,
  "unit": "RMSE K",
  "provenance": "maintainer-run",
  "setting": "T850 day 5, deterministic, IFS ENS (mean) vs Analysis",
  "view": "year 2022, 240x121 grid",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://researchsites.withgoogle.com/weatherbench/deterministic/"
  ]
 },
 {
  "model": "ecmwf-ifs-ens",
  "benchmark": "weatherbench-2",
  "score": 132.3,
  "unit": "RMSE m2/s2",
  "provenance": "maintainer-run",
  "setting": "Z500 day 3, deterministic, IFS ENS (mean) vs Analysis",
  "view": "year 2022, 240x121 grid",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://researchsites.withgoogle.com/weatherbench/deterministic/"
  ]
 },
 {
  "model": "ecmwf-ifs-ens",
  "benchmark": "weatherbench-2",
  "score": 2.761,
  "unit": "RMSE K",
  "provenance": "maintainer-run",
  "setting": "T850 day 10, deterministic, IFS ENS (mean) vs Analysis",
  "view": "year 2022, 240x121 grid",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://researchsites.withgoogle.com/weatherbench/deterministic/"
  ]
 },
 {
  "model": "ecmwf-ifs-ens",
  "benchmark": "weatherbench-2",
  "score": 278.4,
  "unit": "RMSE m2/s2",
  "provenance": "maintainer-run",
  "setting": "Z500 day 5, deterministic, IFS ENS (mean) vs Analysis",
  "view": "year 2022, 240x121 grid",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://researchsites.withgoogle.com/weatherbench/deterministic/"
  ]
 },
 {
  "model": "ecmwf-ifs-ens",
  "benchmark": "weatherbench-2",
  "score": 40.9,
  "unit": "RMSE m2/s2",
  "provenance": "maintainer-run",
  "setting": "Z500 day 1, deterministic, IFS ENS (mean) vs Analysis",
  "view": "year 2022, 240x121 grid",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://researchsites.withgoogle.com/weatherbench/deterministic/"
  ]
 },
 {
  "model": "ecmwf-ifs-ens",
  "benchmark": "weatherbench-2",
  "score": 621.9,
  "unit": "RMSE m2/s2",
  "provenance": "maintainer-run",
  "setting": "Z500 day 10, deterministic, IFS ENS (mean) vs Analysis",
  "view": "year 2022, 240x121 grid",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://researchsites.withgoogle.com/weatherbench/deterministic/"
  ]
 },
 {
  "model": "ecmwf-ifs-hres",
  "benchmark": "weatherbench-2",
  "score": 1.841,
  "unit": "RMSE K",
  "provenance": "maintainer-run",
  "setting": "T850 day 5, deterministic, IFS HRES vs Analysis",
  "view": "year 2022, 240x121 grid",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://researchsites.withgoogle.com/weatherbench/deterministic/"
  ]
 },
 {
  "model": "ecmwf-ifs-hres",
  "benchmark": "weatherbench-2",
  "score": 136.5,
  "unit": "RMSE m2/s2",
  "provenance": "maintainer-run",
  "setting": "Z500 day 3, deterministic, IFS HRES vs Analysis",
  "view": "year 2022, 240x121 grid",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://researchsites.withgoogle.com/weatherbench/deterministic/"
  ]
 },
 {
  "model": "ecmwf-ifs-hres",
  "benchmark": "weatherbench-2",
  "score": 137.2,
  "unit": "RMSE m2/s2",
  "provenance": "maintainer-run",
  "setting": "Z500 day 3, deterministic, IFS HRES vs ERA5",
  "view": "year 2020, 240x121 grid",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://researchsites.withgoogle.com/weatherbench/deterministic/"
  ]
 },
 {
  "model": "ecmwf-ifs-hres",
  "benchmark": "weatherbench-2",
  "score": 3.626,
  "unit": "RMSE K",
  "provenance": "maintainer-run",
  "setting": "T850 day 10, deterministic, IFS HRES vs Analysis",
  "view": "year 2022, 240x121 grid",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://researchsites.withgoogle.com/weatherbench/deterministic/"
  ]
 },
 {
  "model": "ecmwf-ifs-hres",
  "benchmark": "weatherbench-2",
  "score": 305.5,
  "unit": "RMSE m2/s2",
  "provenance": "maintainer-run",
  "setting": "Z500 day 5, deterministic, IFS HRES vs ERA5",
  "view": "year 2020, 240x121 grid",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://researchsites.withgoogle.com/weatherbench/deterministic/"
  ]
 },
 {
  "model": "ecmwf-ifs-hres",
  "benchmark": "weatherbench-2",
  "score": 306.2,
  "unit": "RMSE m2/s2",
  "provenance": "maintainer-run",
  "setting": "Z500 day 5, deterministic, IFS HRES vs Analysis",
  "view": "year 2022, 240x121 grid",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://researchsites.withgoogle.com/weatherbench/deterministic/"
  ]
 },
 {
  "model": "ecmwf-ifs-hres",
  "benchmark": "weatherbench-2",
  "score": 41.2,
  "unit": "RMSE m2/s2",
  "provenance": "maintainer-run",
  "setting": "Z500 day 1, deterministic, IFS HRES vs Analysis",
  "view": "year 2022, 240x121 grid",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://researchsites.withgoogle.com/weatherbench/deterministic/"
  ]
 },
 {
  "model": "ecmwf-ifs-hres",
  "benchmark": "weatherbench-2",
  "score": 47.2,
  "unit": "RMSE m2/s2",
  "provenance": "maintainer-run",
  "setting": "Z500 day 1, deterministic, IFS HRES vs ERA5",
  "view": "year 2020, 240x121 grid",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://researchsites.withgoogle.com/weatherbench/deterministic/"
  ]
 },
 {
  "model": "ecmwf-ifs-hres",
  "benchmark": "weatherbench-2",
  "score": 802.7,
  "unit": "RMSE m2/s2",
  "provenance": "maintainer-run",
  "setting": "Z500 day 10, deterministic, IFS HRES vs ERA5",
  "view": "year 2020, 240x121 grid",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://researchsites.withgoogle.com/weatherbench/deterministic/"
  ]
 },
 {
  "model": "ecmwf-ifs-hres",
  "benchmark": "weatherbench-2",
  "score": 809,
  "unit": "RMSE m2/s2",
  "provenance": "maintainer-run",
  "setting": "Z500 day 10, deterministic, IFS HRES vs Analysis",
  "view": "year 2022, 240x121 grid",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://researchsites.withgoogle.com/weatherbench/deterministic/"
  ]
 },
 {
  "model": "ecnu-qiyao-m",
  "benchmark": "gift-eval",
  "score": 0.461,
  "unit": "CRPS (geo-mean, normalised to Seasonal Naive)",
  "provenance": "independent",
  "setting": "pretrained; rank is average CRPS rank",
  "view": "Leaderboard rebuilt from the published raw results, 143 entries covering all 97 configurations",
  "rank": 34,
  "rank_population": 143,
  "date": "2026-10-09",
  "sources": [
   "https://huggingface.co/spaces/Salesforce/GIFT-Eval"
  ],
  "leakage": "no",
  "leakage_note": "Test Leak. column: No (QiYao-M)"
 },
 {
  "model": "ecnu-qiyao-m",
  "benchmark": "gift-eval",
  "score": 0.671,
  "unit": "MASE (geo-mean, normalised to Seasonal Naive)",
  "provenance": "independent",
  "setting": "pretrained",
  "view": "Leaderboard rebuilt from the published raw results, 143 entries covering all 97 configurations",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-09",
  "sources": [
   "https://huggingface.co/spaces/Salesforce/GIFT-Eval"
  ],
  "leakage": "no",
  "leakage_note": "Test Leak. column: No (QiYao-M)"
 },
 {
  "model": "elevenlabs-eleven-v3",
  "benchmark": "aa-tts",
  "score": 1176,
  "unit": "Elo",
  "provenance": "independent",
  "setting": null,
  "view": "AA Text-to-Speech arena, 96 models",
  "rank": 18,
  "rank_population": 96,
  "date": "2026-10-10",
  "sources": [
   "https://artificialanalysis.ai/text-to-speech/leaderboard"
  ]
 },
 {
  "model": "elevenlabs-eleven-v4-turbo",
  "benchmark": "aa-tts",
  "score": 1327,
  "unit": "Elo",
  "provenance": "independent",
  "setting": null,
  "view": "AA Text-to-Speech arena, 96 models",
  "rank": 1,
  "rank_population": 96,
  "date": "2026-10-10",
  "sources": [
   "https://artificialanalysis.ai/text-to-speech/leaderboard"
  ]
 },
 {
  "model": "elevenlabs-eleven-v4",
  "benchmark": "aa-tts",
  "score": 1323,
  "unit": "Elo",
  "provenance": "independent",
  "setting": null,
  "view": "AA Text-to-Speech arena, 96 models",
  "rank": 2,
  "rank_population": 96,
  "date": "2026-10-10",
  "sources": [
   "https://artificialanalysis.ai/text-to-speech/leaderboard"
  ]
 },
 {
  "model": "emu3-5",
  "benchmark": "geneval",
  "score": 0.86,
  "unit": "score",
  "provenance": "vendor-reported",
  "setting": "paper-reported, labelled unverified by Codesota; year 2025; 34B, AR",
  "view": "Codesota aggregator",
  "rank": 5,
  "rank_population": 7,
  "date": "2025-10-30",
  "sources": [
   "https://arxiv.org/abs/2510.26583",
   "https://www.codesota.com/benchmark/geneval"
  ]
 },
 {
  "model": "epfl-pet-oam-xl",
  "benchmark": "matbench-discovery",
  "score": 0.119,
  "unit": "kSRME",
  "provenance": "maintainer-run",
  "setting": "lower is better",
  "view": "leaderboard fetched 2026-10-10",
  "rank": null,
  "rank_population": null,
  "date": "2026-01-10",
  "sources": [
   "https://matbench-discovery.materialsproject.org/"
  ]
 },
 {
  "model": "epfl-pet-oam-xl",
  "benchmark": "matbench-discovery",
  "score": 0.898,
  "unit": "CPS",
  "provenance": "maintainer-run",
  "setting": null,
  "view": "leaderboard fetched 2026-10-10, ranked by CPS",
  "rank": 1,
  "rank_population": null,
  "date": "2026-01-10",
  "sources": [
   "https://matbench-discovery.materialsproject.org/"
  ]
 },
 {
  "model": "epfl-pet-oam-xl",
  "benchmark": "matbench-discovery",
  "score": 0.924,
  "unit": "F1",
  "provenance": "maintainer-run",
  "setting": null,
  "view": "leaderboard fetched 2026-10-10",
  "rank": null,
  "rank_population": null,
  "date": "2026-01-10",
  "sources": [
   "https://matbench-discovery.materialsproject.org/"
  ]
 },
 {
  "model": "equflash",
  "benchmark": "matbench-discovery",
  "score": 0.158,
  "unit": "kSRME",
  "provenance": "maintainer-run",
  "setting": "lower is better",
  "view": "leaderboard fetched 2026-10-10",
  "rank": null,
  "rank_population": null,
  "date": "2025-06-23",
  "sources": [
   "https://matbench-discovery.materialsproject.org/"
  ]
 },
 {
  "model": "equflash",
  "benchmark": "matbench-discovery",
  "score": 0.888,
  "unit": "CPS",
  "provenance": "maintainer-run",
  "setting": null,
  "view": "leaderboard fetched 2026-10-10, ranked by CPS",
  "rank": 3,
  "rank_population": null,
  "date": "2025-06-23",
  "sources": [
   "https://matbench-discovery.materialsproject.org/"
  ]
 },
 {
  "model": "equflash",
  "benchmark": "matbench-discovery",
  "score": 0.919,
  "unit": "F1",
  "provenance": "maintainer-run",
  "setting": null,
  "view": "leaderboard fetched 2026-10-10",
  "rank": null,
  "rank_population": null,
  "date": "2025-06-23",
  "sources": [
   "https://matbench-discovery.materialsproject.org/"
  ]
 },
 {
  "model": "excarta-heal-vit",
  "benchmark": "weatherbench-2",
  "score": 117.5,
  "unit": "RMSE m2/s2",
  "provenance": "maintainer-run",
  "setting": "Z500 day 3, deterministic, Excarta (HEAL-ViT) vs ERA5",
  "view": "year 2020, 240x121 grid",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://researchsites.withgoogle.com/weatherbench/deterministic/"
  ]
 },
 {
  "model": "excarta-heal-vit",
  "benchmark": "weatherbench-2",
  "score": 271.4,
  "unit": "RMSE m2/s2",
  "provenance": "maintainer-run",
  "setting": "Z500 day 5, deterministic, Excarta (HEAL-ViT) vs ERA5",
  "view": "year 2020, 240x121 grid",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://researchsites.withgoogle.com/weatherbench/deterministic/"
  ]
 },
 {
  "model": "excarta-heal-vit",
  "benchmark": "weatherbench-2",
  "score": 38.7,
  "unit": "RMSE m2/s2",
  "provenance": "maintainer-run",
  "setting": "Z500 day 1, deterministic, Excarta (HEAL-ViT) vs ERA5",
  "view": "year 2020, 240x121 grid",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://researchsites.withgoogle.com/weatherbench/deterministic/"
  ]
 },
 {
  "model": "excarta-heal-vit",
  "benchmark": "weatherbench-2",
  "score": 763.4,
  "unit": "RMSE m2/s2",
  "provenance": "maintainer-run",
  "setting": "Z500 day 10, deterministic, Excarta (HEAL-ViT) vs ERA5",
  "view": "year 2020, 240x121 grid",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://researchsites.withgoogle.com/weatherbench/deterministic/"
  ]
 },
 {
  "model": "figure-ai-helix-2-5",
  "benchmark": "figure-unseen-homes-eval",
  "score": 56,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "Whole-task completion in unseen homes",
  "view": "Vendor (via aiwiki)",
  "rank": null,
  "rank_population": null,
  "date": "2026-09",
  "sources": [
   "https://aiwiki.ai/wiki/helix_vla"
  ]
 },
 {
  "model": "fudan-university-fuxi",
  "benchmark": "weatherbench-2",
  "score": 125.4,
  "unit": "RMSE m2/s2",
  "provenance": "maintainer-run",
  "setting": "Z500 day 3, deterministic, FuXi vs ERA5",
  "view": "year 2020, 240x121 grid",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://researchsites.withgoogle.com/weatherbench/deterministic/"
  ]
 },
 {
  "model": "fudan-university-fuxi",
  "benchmark": "weatherbench-2",
  "score": 277.1,
  "unit": "RMSE m2/s2",
  "provenance": "maintainer-run",
  "setting": "Z500 day 5, deterministic, FuXi vs ERA5",
  "view": "year 2020, 240x121 grid",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://researchsites.withgoogle.com/weatherbench/deterministic/"
  ]
 },
 {
  "model": "fudan-university-fuxi",
  "benchmark": "weatherbench-2",
  "score": 40.1,
  "unit": "RMSE m2/s2",
  "provenance": "maintainer-run",
  "setting": "Z500 day 1, deterministic, FuXi vs ERA5",
  "view": "year 2020, 240x121 grid",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://researchsites.withgoogle.com/weatherbench/deterministic/"
  ]
 },
 {
  "model": "fudan-university-fuxi",
  "benchmark": "weatherbench-2",
  "score": 631.7,
  "unit": "RMSE m2/s2",
  "provenance": "maintainer-run",
  "setting": "Z500 day 10, deterministic, FuXi vs ERA5",
  "view": "year 2020, 240x121 grid",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://researchsites.withgoogle.com/weatherbench/deterministic/"
  ]
 },
 {
  "model": "google-deepmind-alphafold-3",
  "benchmark": "posebusters",
  "score": null,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "Beats Vina docking (P = 2.27e-13); success rate shown only in a figure",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2024-05-08",
  "sources": [
   "https://www.nature.com/articles/s41586-024-07487-w"
  ]
 },
 {
  "model": "google-deepmind-gemini-3-1-pro",
  "benchmark": "aa-intelligence-index",
  "score": 57,
  "unit": "index",
  "provenance": "independent",
  "setting": "v4.0, stale; superseded by AA v4.3.2",
  "view": "DataLearner mirror of AA Index v4.0",
  "rank": 1,
  "rank_population": null,
  "date": "2026-03-26",
  "sources": [
   "https://www.datalearner.com/en/leaderboards/external/aa-quality-index"
  ],
  "unverified": []
 },
 {
  "model": "google-deepmind-gemini-3-1-pro",
  "benchmark": "lmarena-text",
  "score": 1487,
  "unit": "Elo",
  "provenance": "independent",
  "setting": "preview",
  "view": "Arena Text overall",
  "rank": 17,
  "rank_population": null,
  "date": "2026-10-08",
  "sources": [
   "https://arena.ai/leaderboard/chat/text"
  ],
  "uncertainty": "±3"
 },
 {
  "model": "google-deepmind-gemini-3-1-pro",
  "benchmark": "swe-bench-pro",
  "score": 46.1,
  "unit": "%",
  "provenance": "maintainer-run",
  "setting": "Scale SEAL public, mini-swe-agent",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://labs.scale.com/leaderboard/swe_bench_pro_public"
  ],
  "uncertainty": "±3.60"
 },
 {
  "model": "google-deepmind-gemini-3-1-pro",
  "benchmark": "swe-bench-verified",
  "score": 80.6,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://leaderboard.steel.dev/leaderboards/swe-bench-verified.md"
  ]
 },
 {
  "model": "google-deepmind-gemini-3-5-flash",
  "benchmark": "deepswe",
  "score": 37,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://noqta.tn/en/blog/gemini-3-6-flash-antigravity-agentic-coding-2026"
  ]
 },
 {
  "model": "google-deepmind-gemini-3-6-flash",
  "benchmark": "deepswe",
  "score": 49,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://noqta.tn/en/blog/gemini-3-6-flash-antigravity-agentic-coding-2026"
  ]
 },
 {
  "model": "google-deepmind-gemini-3-7-flash",
  "benchmark": "lmarena-vision",
  "score": 1297,
  "unit": "Elo",
  "provenance": "independent",
  "setting": "high; preliminary",
  "view": "Arena Vision overall, style control default, 165 models",
  "rank": 6,
  "rank_population": 165,
  "date": "2026-10-09",
  "sources": [
   "https://arena.ai/leaderboard/chat/vision"
  ],
  "uncertainty": "±10"
 },
 {
  "model": "google-deepmind-gemini-3-8-flash",
  "benchmark": "aa-intelligence-index",
  "score": 41,
  "unit": "index",
  "provenance": "independent",
  "setting": "high; 40.93",
  "view": "AA leaderboard, 205 current models",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://artificialanalysis.ai/leaderboards/models"
  ]
 },
 {
  "model": "google-deepmind-gemini-3-8-flash",
  "benchmark": "deepswe-v1-1",
  "score": 70,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "above 70% (chart only)",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://deepmind.google/models/gemini/flash/"
  ]
 },
 {
  "model": "google-deepmind-gemini-3-8-flash",
  "benchmark": "lmarena-text",
  "score": 1497,
  "unit": "Elo",
  "provenance": "independent",
  "setting": "high",
  "view": "Arena Text overall",
  "rank": 8,
  "rank_population": null,
  "date": "2026-10-08",
  "sources": [
   "https://arena.ai/leaderboard/chat/text"
  ],
  "uncertainty": "±5"
 },
 {
  "model": "google-deepmind-gemini-3-8-flash",
  "benchmark": "lmarena-vision",
  "score": 1289,
  "unit": "Elo",
  "provenance": "independent",
  "setting": "high; preliminary",
  "view": "Arena Vision overall, style control default, 165 models",
  "rank": 14,
  "rank_population": 165,
  "date": "2026-10-09",
  "sources": [
   "https://arena.ai/leaderboard/chat/vision"
  ],
  "uncertainty": "±11"
 },
 {
  "model": "google-deepmind-gemini-3-deep-think",
  "benchmark": "arc-agi-2",
  "score": 45.1,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "With code execution; ARC Prize Verified per vendor",
  "view": "Gemini 3 launch post",
  "rank": null,
  "rank_population": null,
  "date": "2025-11-18",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://blog.google/products/gemini/gemini-3/"
  ]
 },
 {
  "model": "google-deepmind-gemini-3-deep-think",
  "benchmark": "arc-agi-2",
  "score": 84.6,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "Updated Deep Think; verified by the ARC Prize Foundation per vendor",
  "view": "Gemini 3 Deep Think upgrade post",
  "rank": null,
  "rank_population": null,
  "date": "2026-02-12",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://blog.google/innovation-and-ai/models-and-research/gemini-models/gemini-3-deep-think/"
  ]
 },
 {
  "model": "google-deepmind-gemini-3-deep-think",
  "benchmark": "codeforces",
  "score": 3455,
  "unit": "Elo",
  "provenance": "vendor-reported",
  "setting": "Updated Deep Think",
  "view": "Gemini 3 Deep Think upgrade post",
  "rank": null,
  "rank_population": null,
  "date": "2026-02-12",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://blog.google/innovation-and-ai/models-and-research/gemini-models/gemini-3-deep-think/"
  ]
 },
 {
  "model": "google-deepmind-gemini-3-deep-think",
  "benchmark": "gpqa-diamond",
  "score": 93.8,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": "Gemini 3 launch post",
  "rank": null,
  "rank_population": null,
  "date": "2025-11-18",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://blog.google/products/gemini/gemini-3/"
  ]
 },
 {
  "model": "google-deepmind-gemini-3-deep-think",
  "benchmark": "hle",
  "score": 41,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "Without tools",
  "view": "Gemini 3 launch post",
  "rank": null,
  "rank_population": null,
  "date": "2025-11-18",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://blog.google/products/gemini/gemini-3/"
  ]
 },
 {
  "model": "google-deepmind-gemini-3-deep-think",
  "benchmark": "hle",
  "score": 48.4,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "Without tools; updated Deep Think",
  "view": "Gemini 3 Deep Think upgrade post",
  "rank": null,
  "rank_population": null,
  "date": "2026-02-12",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://blog.google/innovation-and-ai/models-and-research/gemini-models/gemini-3-deep-think/"
  ]
 },
 {
  "model": "google-deepmind-gemini-3-pro",
  "benchmark": "mmmu",
  "score": 87.2,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": "BenchLM aggregator, top score",
  "rank": 1,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://www.benchlm.ai/benchmarks/mmmu"
  ],
  "unverified": []
 },
 {
  "model": "google-deepmind-gemini-3-pro",
  "benchmark": "omnidocbench-v1-6",
  "score": 92.91,
  "unit": "score",
  "provenance": "vendor-reported",
  "setting": "overall",
  "view": "PaddleOCR-VL-1.6 paper table",
  "rank": null,
  "rank_population": null,
  "date": "2026-06-02",
  "sources": [
   "https://arxiv.org/pdf/2606.03264"
  ]
 },
 {
  "model": "google-deepmind-gemini-3-pro",
  "benchmark": "real5-omnidocbench",
  "score": 89.24,
  "unit": "score",
  "provenance": "vendor-reported",
  "setting": "overall",
  "view": "PaddleOCR-VL-1.6 paper table",
  "rank": null,
  "rank_population": null,
  "date": "2026-06-02",
  "sources": [
   "https://arxiv.org/pdf/2606.03264"
  ]
 },
 {
  "model": "google-deepmind-gemini-4-argon",
  "benchmark": "aa-intelligence-index",
  "score": 53,
  "unit": "index",
  "provenance": "independent",
  "setting": "high; 52.56 per secondary",
  "view": "AA leaderboard, 205 current models",
  "rank": 8,
  "rank_population": 205,
  "date": "2026-10-10",
  "sources": [
   "https://artificialanalysis.ai/leaderboards/models"
  ]
 },
 {
  "model": "google-deepmind-gemini-4-argon",
  "benchmark": "automationbench",
  "score": 51.3,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "Google self-reported",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://www.orcarouter.ai/es/blog/gemini-4-argon"
  ]
 },
 {
  "model": "google-deepmind-gemini-4-argon",
  "benchmark": "benchlm-composite",
  "score": 81.8,
  "unit": "index",
  "provenance": "vendor-reported",
  "setting": "estimated",
  "view": "benchlm.ai frontier top 6",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-09",
  "sources": [
   "https://benchlm.ai/frontier-ai-models"
  ]
 },
 {
  "model": "google-deepmind-gemini-4-argon",
  "benchmark": "deepswe-v1-1",
  "score": 77.9,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "Google self-reported",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://www.orcarouter.ai/es/blog/gemini-4-argon"
  ]
 },
 {
  "model": "google-deepmind-gemini-4-argon",
  "benchmark": "harvey-legal-agent-benchmark",
  "score": 19.6,
  "unit": null,
  "provenance": "vendor-reported",
  "setting": "Google self-reported",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://www.orcarouter.ai/es/blog/gemini-4-argon"
  ]
 },
 {
  "model": "google-deepmind-gemini-4-argon",
  "benchmark": "labbench-2",
  "score": 88.8,
  "unit": null,
  "provenance": "vendor-reported",
  "setting": "Google self-reported",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://www.orcarouter.ai/es/blog/gemini-4-argon"
  ]
 },
 {
  "model": "google-deepmind-gemini-4-argon",
  "benchmark": "lmarena-text",
  "score": 1525,
  "unit": "Elo",
  "provenance": "independent",
  "setting": "high",
  "view": "Arena Text overall",
  "rank": 1,
  "rank_population": null,
  "date": "2026-10-08",
  "sources": [
   "https://arena.ai/leaderboard/chat/text",
   "https://arena.ai/leaderboard/text"
  ],
  "uncertainty": "±9",
  "unverified": []
 },
 {
  "model": "google-deepmind-gemini-4-argon",
  "benchmark": "vals-index",
  "score": 68.9,
  "unit": null,
  "provenance": "vendor-reported",
  "setting": "Google self-reported",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://www.orcarouter.ai/es/blog/gemini-4-argon"
  ]
 },
 {
  "model": "google-deepmind-gemini-omni-flash",
  "benchmark": "lmarena-text-to-video",
  "score": 1513,
  "unit": "Elo",
  "provenance": "independent",
  "setting": null,
  "view": "LMArena Text-to-Video, updated 21 Sep 2026",
  "rank": 2,
  "rank_population": null,
  "date": "2026-09-21",
  "sources": [
   "https://arena.ai/leaderboard/text-to-video"
  ],
  "uncertainty": "±9"
 },
 {
  "model": "google-deepmind-gemini-robotics-2-vla",
  "benchmark": "gemini-robotics-2-vendor-evals",
  "score": 45.7,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "Apollo 2 whole-body pick, floor",
  "view": "Vendor, Jul 2026 (via aiwiki)",
  "rank": null,
  "rank_population": null,
  "date": "2026-07",
  "sources": [
   "https://aiwiki.ai/wiki/gemini_robotics_2"
  ]
 },
 {
  "model": "google-deepmind-gemini-robotics-2-vla",
  "benchmark": "gemini-robotics-2-vendor-evals",
  "score": 68.4,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "Apollo 2 whole-body pick, table",
  "view": "Vendor, Jul 2026 (via aiwiki)",
  "rank": null,
  "rank_population": null,
  "date": "2026-07",
  "sources": [
   "https://aiwiki.ai/wiki/gemini_robotics_2"
  ]
 },
 {
  "model": "google-deepmind-gemini-robotics-2-vla",
  "benchmark": "gemini-robotics-2-vendor-evals",
  "score": 74.2,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "Franka Duo pick-and-place",
  "view": "Vendor, Jul 2026 (via aiwiki)",
  "rank": null,
  "rank_population": null,
  "date": "2026-07",
  "sources": [
   "https://aiwiki.ai/wiki/gemini_robotics_2"
  ]
 },
 {
  "model": "google-deepmind-gemini-robotics-2-vla",
  "benchmark": "gemini-robotics-2-vendor-evals",
  "score": 76.3,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "Apollo 2 whole-body pick, shelf",
  "view": "Vendor, Jul 2026 (via aiwiki)",
  "rank": null,
  "rank_population": null,
  "date": "2026-07",
  "sources": [
   "https://aiwiki.ai/wiki/gemini_robotics_2"
  ]
 },
 {
  "model": "google-deepmind-gemini-robotics-2-vla",
  "benchmark": "gemini-robotics-2-vendor-evals",
  "score": 89.6,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "Franka Duo precise insertion",
  "view": "Vendor, Jul 2026 (via aiwiki)",
  "rank": null,
  "rank_population": null,
  "date": "2026-07",
  "sources": [
   "https://aiwiki.ai/wiki/gemini_robotics_2"
  ]
 },
 {
  "model": "google-deepmind-gemini-robotics-er-2",
  "benchmark": "gemini-robotics-2-vendor-evals",
  "score": 91.3,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "Moment finding",
  "view": "Vendor, Jul 2026 (via aiwiki)",
  "rank": null,
  "rank_population": null,
  "date": "2026-07",
  "sources": [
   "https://aiwiki.ai/wiki/gemini_robotics_2"
  ]
 },
 {
  "model": "google-deepmind-gencast",
  "benchmark": "weatherbench-2",
  "score": 1.477,
  "unit": "RMSE K",
  "provenance": "maintainer-run",
  "setting": "T850 day 5, deterministic, GenCast (oper.) (mean) vs Analysis",
  "view": "year 2022, 240x121 grid",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://researchsites.withgoogle.com/weatherbench/deterministic/"
  ]
 },
 {
  "model": "google-deepmind-gencast",
  "benchmark": "weatherbench-2",
  "score": 123.5,
  "unit": "RMSE m2/s2",
  "provenance": "maintainer-run",
  "setting": "Z500 day 3, deterministic, GenCast (mean) vs ERA5",
  "view": "year 2020, 240x121 grid",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://researchsites.withgoogle.com/weatherbench/deterministic/"
  ]
 },
 {
  "model": "google-deepmind-gencast",
  "benchmark": "weatherbench-2",
  "score": 124.3,
  "unit": "RMSE m2/s2",
  "provenance": "maintainer-run",
  "setting": "Z500 day 3, deterministic, GenCast (oper.) (mean) vs Analysis",
  "view": "year 2022, 240x121 grid",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://researchsites.withgoogle.com/weatherbench/deterministic/"
  ]
 },
 {
  "model": "google-deepmind-gencast",
  "benchmark": "weatherbench-2",
  "score": 2.693,
  "unit": "RMSE K",
  "provenance": "maintainer-run",
  "setting": "T850 day 10, deterministic, GenCast (oper.) (mean) vs Analysis",
  "view": "year 2022, 240x121 grid",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://researchsites.withgoogle.com/weatherbench/deterministic/"
  ]
 },
 {
  "model": "google-deepmind-gencast",
  "benchmark": "weatherbench-2",
  "score": 262.4,
  "unit": "RMSE m2/s2",
  "provenance": "maintainer-run",
  "setting": "Z500 day 5, deterministic, GenCast (mean) vs ERA5",
  "view": "year 2020, 240x121 grid",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://researchsites.withgoogle.com/weatherbench/deterministic/"
  ]
 },
 {
  "model": "google-deepmind-gencast",
  "benchmark": "weatherbench-2",
  "score": 264.7,
  "unit": "RMSE m2/s2",
  "provenance": "maintainer-run",
  "setting": "Z500 day 5, deterministic, GenCast (oper.) (mean) vs Analysis",
  "view": "year 2022, 240x121 grid",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://researchsites.withgoogle.com/weatherbench/deterministic/"
  ]
 },
 {
  "model": "google-deepmind-gencast",
  "benchmark": "weatherbench-2",
  "score": 39.2,
  "unit": "RMSE m2/s2",
  "provenance": "maintainer-run",
  "setting": "Z500 day 1, deterministic, GenCast (oper.) (mean) vs Analysis",
  "view": "year 2022, 240x121 grid",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://researchsites.withgoogle.com/weatherbench/deterministic/"
  ]
 },
 {
  "model": "google-deepmind-gencast",
  "benchmark": "weatherbench-2",
  "score": 39.3,
  "unit": "RMSE m2/s2",
  "provenance": "maintainer-run",
  "setting": "Z500 day 1, deterministic, GenCast (mean) vs ERA5",
  "view": "year 2020, 240x121 grid",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://researchsites.withgoogle.com/weatherbench/deterministic/"
  ]
 },
 {
  "model": "google-deepmind-gencast",
  "benchmark": "weatherbench-2",
  "score": 606.5,
  "unit": "RMSE m2/s2",
  "provenance": "maintainer-run",
  "setting": "Z500 day 10, deterministic, GenCast (mean) vs ERA5",
  "view": "year 2020, 240x121 grid",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://researchsites.withgoogle.com/weatherbench/deterministic/"
  ]
 },
 {
  "model": "google-deepmind-gencast",
  "benchmark": "weatherbench-2",
  "score": 607.5,
  "unit": "RMSE m2/s2",
  "provenance": "maintainer-run",
  "setting": "Z500 day 10, deterministic, GenCast (oper.) (mean) vs Analysis",
  "view": "year 2022, 240x121 grid",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://researchsites.withgoogle.com/weatherbench/deterministic/"
  ]
 },
 {
  "model": "google-deepmind-graphcast",
  "benchmark": "weatherbench-2",
  "score": 1.555,
  "unit": "RMSE K",
  "provenance": "maintainer-run",
  "setting": "T850 day 5, deterministic, GraphCast (oper.) vs Analysis",
  "view": "year 2022, 240x121 grid",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://researchsites.withgoogle.com/weatherbench/deterministic/"
  ]
 },
 {
  "model": "google-deepmind-graphcast",
  "benchmark": "weatherbench-2",
  "score": 120.6,
  "unit": "RMSE m2/s2",
  "provenance": "maintainer-run",
  "setting": "Z500 day 3, deterministic, GraphCast (oper.) vs Analysis",
  "view": "year 2022, 240x121 grid",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://researchsites.withgoogle.com/weatherbench/deterministic/"
  ]
 },
 {
  "model": "google-deepmind-graphcast",
  "benchmark": "weatherbench-2",
  "score": 124.2,
  "unit": "RMSE m2/s2",
  "provenance": "maintainer-run",
  "setting": "Z500 day 3, deterministic, GraphCast vs ERA5",
  "view": "year 2020, 240x121 grid",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://researchsites.withgoogle.com/weatherbench/deterministic/"
  ]
 },
 {
  "model": "google-deepmind-graphcast",
  "benchmark": "weatherbench-2",
  "score": 270.2,
  "unit": "RMSE m2/s2",
  "provenance": "maintainer-run",
  "setting": "Z500 day 5, deterministic, GraphCast (oper.) vs Analysis",
  "view": "year 2022, 240x121 grid",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://researchsites.withgoogle.com/weatherbench/deterministic/"
  ]
 },
 {
  "model": "google-deepmind-graphcast",
  "benchmark": "weatherbench-2",
  "score": 274.3,
  "unit": "RMSE m2/s2",
  "provenance": "maintainer-run",
  "setting": "Z500 day 5, deterministic, GraphCast vs ERA5",
  "view": "year 2020, 240x121 grid",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://researchsites.withgoogle.com/weatherbench/deterministic/"
  ]
 },
 {
  "model": "google-deepmind-graphcast",
  "benchmark": "weatherbench-2",
  "score": 3.364,
  "unit": "RMSE K",
  "provenance": "maintainer-run",
  "setting": "T850 day 10, deterministic, GraphCast (oper.) vs Analysis",
  "view": "year 2022, 240x121 grid",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://researchsites.withgoogle.com/weatherbench/deterministic/"
  ]
 },
 {
  "model": "google-deepmind-graphcast",
  "benchmark": "weatherbench-2",
  "score": 38.3,
  "unit": "RMSE m2/s2",
  "provenance": "maintainer-run",
  "setting": "Z500 day 1, deterministic, GraphCast (oper.) vs Analysis",
  "view": "year 2022, 240x121 grid",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://researchsites.withgoogle.com/weatherbench/deterministic/"
  ]
 },
 {
  "model": "google-deepmind-graphcast",
  "benchmark": "weatherbench-2",
  "score": 39.8,
  "unit": "RMSE m2/s2",
  "provenance": "maintainer-run",
  "setting": "Z500 day 1, deterministic, GraphCast vs ERA5",
  "view": "year 2020, 240x121 grid",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://researchsites.withgoogle.com/weatherbench/deterministic/"
  ]
 },
 {
  "model": "google-deepmind-graphcast",
  "benchmark": "weatherbench-2",
  "score": 731.9,
  "unit": "RMSE m2/s2",
  "provenance": "maintainer-run",
  "setting": "Z500 day 10, deterministic, GraphCast vs ERA5",
  "view": "year 2020, 240x121 grid",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://researchsites.withgoogle.com/weatherbench/deterministic/"
  ]
 },
 {
  "model": "google-deepmind-graphcast",
  "benchmark": "weatherbench-2",
  "score": 747.6,
  "unit": "RMSE m2/s2",
  "provenance": "maintainer-run",
  "setting": "Z500 day 10, deterministic, GraphCast (oper.) vs Analysis",
  "view": "year 2022, 240x121 grid",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://researchsites.withgoogle.com/weatherbench/deterministic/"
  ]
 },
 {
  "model": "google-deepmind-lyria-2",
  "benchmark": "aa-music-arena-v1-1",
  "score": 932,
  "unit": "Elo",
  "provenance": "independent",
  "setting": "secondary capture of AA post",
  "view": "AA Music Arena v1.1, board not stated",
  "rank": null,
  "rank_population": null,
  "date": "2026-10",
  "sources": [
   "https://alphasignal.ai/news/artificial-analysis-music-arena-v1-1-crowns-suno-v6-across-1-000-harder-prompts",
   "https://digg.com/ai/g8egglmo"
  ]
 },
 {
  "model": "google-deepmind-lyria-3-5",
  "benchmark": "aa-music-arena-v1-1",
  "score": 1076,
  "unit": "Elo",
  "provenance": "independent",
  "setting": "secondary capture of AA post; tied 3-6",
  "view": "AA Music Arena v1.1, Instrumental",
  "rank": 3,
  "rank_population": null,
  "date": "2026-10",
  "sources": [
   "https://alphasignal.ai/news/artificial-analysis-music-arena-v1-1-crowns-suno-v6-across-1-000-harder-prompts",
   "https://digg.com/ai/g8egglmo"
  ]
 },
 {
  "model": "google-deepmind-lyria-3-pro",
  "benchmark": "aa-music-arena-v1-1",
  "score": 1078,
  "unit": "Elo",
  "provenance": "independent",
  "setting": "secondary capture of AA post; tied 3-6",
  "view": "AA Music Arena v1.1, Instrumental",
  "rank": 3,
  "rank_population": null,
  "date": "2026-10",
  "sources": [
   "https://alphasignal.ai/news/artificial-analysis-music-arena-v1-1-crowns-suno-v6-across-1-000-harder-prompts",
   "https://digg.com/ai/g8egglmo"
  ]
 },
 {
  "model": "google-deepmind-nano-banana-2-1",
  "benchmark": "aa-image-t2i-v2-0",
  "score": 1160,
  "unit": "Elo",
  "provenance": "independent",
  "setting": "rank shown as 4-6",
  "view": "AA Text-to-Image Arena, overall",
  "rank": 4,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://artificialanalysis.ai/text-to-image/arena/leaderboard-text"
  ]
 },
 {
  "model": "google-deepmind-nano-banana-2-1",
  "benchmark": "lmarena-text-to-image",
  "score": 1328,
  "unit": "Elo",
  "provenance": "independent",
  "setting": "preliminary",
  "view": "LMArena Text-to-Image, overall, updated 7 Oct 2026",
  "rank": 6,
  "rank_population": null,
  "date": "2026-10-07",
  "sources": [
   "https://arena.ai/leaderboard/text-to-image"
  ],
  "uncertainty": "±9"
 },
 {
  "model": "google-deepmind-veo-3-1",
  "benchmark": "aa-video-t2v",
  "score": 962,
  "unit": "Elo",
  "provenance": "independent",
  "setting": null,
  "view": "AA Text-to-Video leaderboard",
  "rank": 19,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://artificialanalysis.ai/video/leaderboard/text-to-video"
  ]
 },
 {
  "model": "google-deepmind-veo-3-1",
  "benchmark": "lmarena-text-to-video",
  "score": 1364,
  "unit": "Elo",
  "provenance": "independent",
  "setting": "veo-3.1-audio",
  "view": "LMArena Text-to-Video, updated 21 Sep 2026",
  "rank": 12,
  "rank_population": null,
  "date": "2026-09-21",
  "sources": [
   "https://arena.ai/leaderboard/text-to-video"
  ],
  "uncertainty": "±14"
 },
 {
  "model": "google-deepmind-veo-3",
  "benchmark": "vbench-2-0",
  "score": 60.85,
  "unit": "%",
  "provenance": "maintainer-run",
  "setting": "Creativity score",
  "view": "VBench-2.0",
  "rank": null,
  "rank_population": null,
  "date": "2025-09-04",
  "sources": [
   "https://huggingface.co/spaces/Vchitect/VBench_Leaderboard"
  ]
 },
 {
  "model": "google-deepmind-veo-3",
  "benchmark": "vbench-2-0",
  "score": 66.72,
  "unit": "%",
  "provenance": "maintainer-run",
  "setting": "Total score",
  "view": "VBench-2.0",
  "rank": 1,
  "rank_population": null,
  "date": "2025-09-04",
  "sources": [
   "https://huggingface.co/spaces/Vchitect/VBench_Leaderboard"
  ]
 },
 {
  "model": "google-deepmind-veo-3",
  "benchmark": "vbench",
  "score": 85.06,
  "unit": "%",
  "provenance": "maintainer-run",
  "setting": "Total score; submission-based board",
  "view": "VBench (v1) text-to-video",
  "rank": 9,
  "rank_population": null,
  "date": "2025-08-06",
  "sources": [
   "https://huggingface.co/spaces/Vchitect/VBench_Leaderboard"
  ]
 },
 {
  "model": "google-deepmind-veo-3",
  "benchmark": "vbench",
  "score": 85.7,
  "unit": "%",
  "provenance": "maintainer-run",
  "setting": "Quality score; submission-based board",
  "view": "VBench (v1) text-to-video",
  "rank": null,
  "rank_population": null,
  "date": "2025-08-06",
  "sources": [
   "https://huggingface.co/spaces/Vchitect/VBench_Leaderboard"
  ]
 },
 {
  "model": "google-deepmind-weathernext-2",
  "benchmark": "weatherbench-2",
  "score": 1.348,
  "unit": "RMSE K",
  "provenance": "maintainer-run",
  "setting": "T850 day 5, deterministic, FGN (oper.) (mean) vs Analysis",
  "view": "year 2022, 240x121 grid",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://researchsites.withgoogle.com/weatherbench/deterministic/"
  ]
 },
 {
  "model": "google-deepmind-weathernext-2",
  "benchmark": "weatherbench-2",
  "score": 1.81,
  "unit": "RMSE K",
  "provenance": "maintainer-run",
  "setting": "T850 day 5, deterministic, FGN (oper.) (1st member) vs Analysis",
  "view": "year 2022, 240x121 grid",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://researchsites.withgoogle.com/weatherbench/deterministic/"
  ]
 },
 {
  "model": "google-deepmind-weathernext-2",
  "benchmark": "weatherbench-2",
  "score": 104.5,
  "unit": "RMSE m2/s2",
  "provenance": "maintainer-run",
  "setting": "Z500 day 3, deterministic, FGN (oper.) (mean) vs Analysis",
  "view": "year 2022, 240x121 grid",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://researchsites.withgoogle.com/weatherbench/deterministic/"
  ]
 },
 {
  "model": "google-deepmind-weathernext-2",
  "benchmark": "weatherbench-2",
  "score": 139.4,
  "unit": "RMSE m2/s2",
  "provenance": "maintainer-run",
  "setting": "Z500 day 3, deterministic, FGN (oper.) (1st member) vs Analysis",
  "view": "year 2022, 240x121 grid",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://researchsites.withgoogle.com/weatherbench/deterministic/"
  ]
 },
 {
  "model": "google-deepmind-weathernext-2",
  "benchmark": "weatherbench-2",
  "score": 2.595,
  "unit": "RMSE K",
  "provenance": "maintainer-run",
  "setting": "T850 day 10, deterministic, FGN (oper.) (mean) vs Analysis",
  "view": "year 2022, 240x121 grid",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://researchsites.withgoogle.com/weatherbench/deterministic/"
  ]
 },
 {
  "model": "google-deepmind-weathernext-2",
  "benchmark": "weatherbench-2",
  "score": 233.1,
  "unit": "RMSE m2/s2",
  "provenance": "maintainer-run",
  "setting": "Z500 day 5, deterministic, FGN (oper.) (mean) vs Analysis",
  "view": "year 2022, 240x121 grid",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://researchsites.withgoogle.com/weatherbench/deterministic/"
  ]
 },
 {
  "model": "google-deepmind-weathernext-2",
  "benchmark": "weatherbench-2",
  "score": 3.632,
  "unit": "RMSE K",
  "provenance": "maintainer-run",
  "setting": "T850 day 10, deterministic, FGN (oper.) (1st member) vs Analysis",
  "view": "year 2022, 240x121 grid",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://researchsites.withgoogle.com/weatherbench/deterministic/"
  ]
 },
 {
  "model": "google-deepmind-weathernext-2",
  "benchmark": "weatherbench-2",
  "score": 313.7,
  "unit": "RMSE m2/s2",
  "provenance": "maintainer-run",
  "setting": "Z500 day 5, deterministic, FGN (oper.) (1st member) vs Analysis",
  "view": "year 2022, 240x121 grid",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://researchsites.withgoogle.com/weatherbench/deterministic/"
  ]
 },
 {
  "model": "google-deepmind-weathernext-2",
  "benchmark": "weatherbench-2",
  "score": 32.3,
  "unit": "RMSE m2/s2",
  "provenance": "maintainer-run",
  "setting": "Z500 day 1, deterministic, FGN (oper.) (mean) vs Analysis",
  "view": "year 2022, 240x121 grid",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://researchsites.withgoogle.com/weatherbench/deterministic/"
  ]
 },
 {
  "model": "google-deepmind-weathernext-2",
  "benchmark": "weatherbench-2",
  "score": 43.7,
  "unit": "RMSE m2/s2",
  "provenance": "maintainer-run",
  "setting": "Z500 day 1, deterministic, FGN (oper.) (1st member) vs Analysis",
  "view": "year 2022, 240x121 grid",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://researchsites.withgoogle.com/weatherbench/deterministic/"
  ]
 },
 {
  "model": "google-deepmind-weathernext-2",
  "benchmark": "weatherbench-2",
  "score": 583.1,
  "unit": "RMSE m2/s2",
  "provenance": "maintainer-run",
  "setting": "Z500 day 10, deterministic, FGN (oper.) (mean) vs Analysis",
  "view": "year 2022, 240x121 grid",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://researchsites.withgoogle.com/weatherbench/deterministic/"
  ]
 },
 {
  "model": "google-deepmind-weathernext-2",
  "benchmark": "weatherbench-2",
  "score": 811.7,
  "unit": "RMSE m2/s2",
  "provenance": "maintainer-run",
  "setting": "Z500 day 10, deterministic, FGN (oper.) (1st member) vs Analysis",
  "view": "year 2022, 240x121 grid",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://researchsites.withgoogle.com/weatherbench/deterministic/"
  ]
 },
 {
  "model": "google-embeddinggemma-2",
  "benchmark": "mteb-code",
  "score": 78.68,
  "unit": "score",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/google/embeddinggemma-2"
  ]
 },
 {
  "model": "google-embeddinggemma-2",
  "benchmark": "mteb-english-v2",
  "score": 68.46,
  "unit": "score",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/google/embeddinggemma-2"
  ]
 },
 {
  "model": "google-embeddinggemma-2",
  "benchmark": "mteb-multilingual-v2",
  "score": 61.36,
  "unit": "score",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/google/embeddinggemma-2"
  ]
 },
 {
  "model": "google-gemini-3-8-flash-lite-tts",
  "benchmark": "aa-tts",
  "score": 1244,
  "unit": "Elo",
  "provenance": "independent",
  "setting": null,
  "view": "AA Text-to-Speech arena, 96 models",
  "rank": 8,
  "rank_population": 96,
  "date": "2026-10-10",
  "sources": [
   "https://artificialanalysis.ai/text-to-speech/leaderboard"
  ]
 },
 {
  "model": "google-gemini-3-8-flash-tts",
  "benchmark": "aa-tts",
  "score": 1272,
  "unit": "Elo",
  "provenance": "independent",
  "setting": null,
  "view": "AA Text-to-Speech arena, 96 models",
  "rank": 5,
  "rank_population": 96,
  "date": "2026-10-10",
  "sources": [
   "https://artificialanalysis.ai/text-to-speech/leaderboard"
  ]
 },
 {
  "model": "google-gemini-3-flash",
  "benchmark": "omnidocbench-v1-6",
  "score": 92.62,
  "unit": "score",
  "provenance": "vendor-reported",
  "setting": "overall",
  "view": "PaddleOCR-VL-1.6 paper table",
  "rank": null,
  "rank_population": null,
  "date": "2026-06-02",
  "sources": [
   "https://arxiv.org/pdf/2606.03264"
  ]
 },
 {
  "model": "google-gemini-nano-banana-2-1",
  "benchmark": "lmarena-text-to-image",
  "score": null,
  "unit": null,
  "provenance": "independent",
  "setting": null,
  "view": "Arena Text-to-Image",
  "rank": 6,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://arena.ai/leaderboard"
  ],
  "unverified": []
 },
 {
  "model": "google-gemini-omni-flash-1-1",
  "benchmark": "aa-video-t2v",
  "score": 1113,
  "unit": "Elo",
  "provenance": "independent",
  "setting": null,
  "view": "AA Text-to-Video leaderboard",
  "rank": 8,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://artificialanalysis.ai/video/leaderboard/text-to-video"
  ]
 },
 {
  "model": "google-gemini-omni-flash-1-1",
  "benchmark": "lmarena-text-to-video",
  "score": 1516,
  "unit": "Elo",
  "provenance": "independent",
  "setting": "gemini-omni-1.1-flash",
  "view": "LMArena Text-to-Video, updated 21 Sep 2026",
  "rank": 1,
  "rank_population": null,
  "date": "2026-09-21",
  "sources": [
   "https://arena.ai/leaderboard/text-to-video"
  ],
  "uncertainty": "±15"
 },
 {
  "model": "google-gemma-3-27b-it",
  "benchmark": "sea-helm",
  "score": 64.54,
  "unit": "score",
  "provenance": "maintainer-run",
  "setting": "Checkpoint gemma-3-27b-it as listed; release view (data last updated 18 Sep 2026); score is the average of 2000 bootstraps",
  "view": "SEA-HELM leaderboard, 58 models, SEA average",
  "rank": null,
  "rank_population": null,
  "date": "2026-09-18",
  "uncertainty": "95% CI [-0.74, +0.72]",
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://leaderboard.sea-lion.ai/detailed/SEA"
  ]
 },
 {
  "model": "google-gemma-3-27b-it",
  "benchmark": "sea-helm",
  "score": 70.41,
  "unit": "score",
  "provenance": "maintainer-run",
  "setting": "Checkpoint gemma-3-27b-it as listed; release view (data last updated 18 Sep 2026); score is the average of 2000 bootstraps",
  "view": "SEA-HELM leaderboard, 58 models, Indonesian (ID)",
  "rank": null,
  "rank_population": null,
  "date": "2026-09-18",
  "uncertainty": "95% CI [-1.47, +1.49]",
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://leaderboard.sea-lion.ai/detailed/ID"
  ]
 },
 {
  "model": "google-gemma-3-4b-it",
  "benchmark": "sea-helm",
  "score": 47.84,
  "unit": "score",
  "provenance": "maintainer-run",
  "setting": "Checkpoint gemma-3-4b-it as listed; release view (data last updated 18 Sep 2026); score is the average of 2000 bootstraps",
  "view": "SEA-HELM leaderboard, 58 models, SEA average",
  "rank": null,
  "rank_population": null,
  "date": "2026-09-18",
  "uncertainty": "95% CI [-0.75, +0.74]",
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://leaderboard.sea-lion.ai/detailed/SEA"
  ]
 },
 {
  "model": "google-gemma-3-4b-it",
  "benchmark": "sea-helm",
  "score": 57.71,
  "unit": "score",
  "provenance": "maintainer-run",
  "setting": "Checkpoint gemma-3-4b-it as listed; release view (data last updated 18 Sep 2026); score is the average of 2000 bootstraps",
  "view": "SEA-HELM leaderboard, 58 models, Indonesian (ID)",
  "rank": null,
  "rank_population": null,
  "date": "2026-09-18",
  "uncertainty": "95% CI [-1.76, +1.67]",
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://leaderboard.sea-lion.ai/detailed/ID"
  ]
 },
 {
  "model": "google-gemma-3-4b",
  "benchmark": "medqa",
  "score": 50.7,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "Baseline in MedGemma report",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2025-07",
  "sources": [
   "https://arxiv.org/html/2507.05201v2"
  ]
 },
 {
  "model": "google-gemma-3n-e2b",
  "benchmark": "arc-c",
  "score": 51.7,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "PT (pretrained checkpoint)",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://ai.google.dev/gemma/docs/gemma-3n/model_card"
  ],
  "unverified": []
 },
 {
  "model": "google-gemma-3n-e2b",
  "benchmark": "global-mmlu",
  "score": 55.1,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "IT",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://ai.google.dev/gemma/docs/gemma-3n/model_card"
  ],
  "unverified": []
 },
 {
  "model": "google-gemma-3n-e2b",
  "benchmark": "gpqa-diamond",
  "score": 24.8,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "IT",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://ai.google.dev/gemma/docs/gemma-3n/model_card"
  ],
  "unverified": []
 },
 {
  "model": "google-gemma-3n-e2b",
  "benchmark": "hellaswag",
  "score": 72.2,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "PT (pretrained checkpoint)",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://ai.google.dev/gemma/docs/gemma-3n/model_card"
  ],
  "unverified": []
 },
 {
  "model": "google-gemma-3n-e2b",
  "benchmark": "livecodebench-v5",
  "score": 18.6,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "IT",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://ai.google.dev/gemma/docs/gemma-3n/model_card"
  ],
  "unverified": []
 },
 {
  "model": "google-gemma-3n-e2b",
  "benchmark": "mgsm",
  "score": 53.1,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "IT",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://ai.google.dev/gemma/docs/gemma-3n/model_card"
  ],
  "unverified": []
 },
 {
  "model": "google-gemma-3n-e4b",
  "benchmark": "arc-c",
  "score": 61.6,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "PT (pretrained checkpoint)",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://ai.google.dev/gemma/docs/gemma-3n/model_card"
  ],
  "unverified": []
 },
 {
  "model": "google-gemma-3n-e4b",
  "benchmark": "global-mmlu",
  "score": 60.3,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "IT",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://ai.google.dev/gemma/docs/gemma-3n/model_card"
  ],
  "unverified": []
 },
 {
  "model": "google-gemma-3n-e4b",
  "benchmark": "gpqa-diamond",
  "score": 23.7,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "IT",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://ai.google.dev/gemma/docs/gemma-3n/model_card"
  ],
  "unverified": []
 },
 {
  "model": "google-gemma-3n-e4b",
  "benchmark": "hellaswag",
  "score": 78.6,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "PT (pretrained checkpoint)",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://ai.google.dev/gemma/docs/gemma-3n/model_card"
  ],
  "unverified": []
 },
 {
  "model": "google-gemma-3n-e4b",
  "benchmark": "livecodebench-v5",
  "score": 25.7,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "IT",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://ai.google.dev/gemma/docs/gemma-3n/model_card"
  ],
  "unverified": []
 },
 {
  "model": "google-gemma-3n-e4b",
  "benchmark": "mgsm",
  "score": 60.7,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "IT",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://ai.google.dev/gemma/docs/gemma-3n/model_card"
  ],
  "unverified": []
 },
 {
  "model": "google-gemma-4-12b",
  "benchmark": "sea-helm",
  "score": 69.31,
  "unit": "score",
  "provenance": "maintainer-run",
  "setting": "Checkpoint gemma-4-12B-it as listed; release view (data last updated 18 Sep 2026); score is the average of 2000 bootstraps",
  "view": "SEA-HELM leaderboard, 58 models, SEA average",
  "rank": null,
  "rank_population": null,
  "date": "2026-09-18",
  "uncertainty": "95% CI [-0.64, +0.67]",
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://leaderboard.sea-lion.ai/detailed/SEA"
  ]
 },
 {
  "model": "google-gemma-4-12b",
  "benchmark": "sea-helm",
  "score": 74.51,
  "unit": "score",
  "provenance": "maintainer-run",
  "setting": "Checkpoint gemma-4-12B-it as listed; release view (data last updated 18 Sep 2026); score is the average of 2000 bootstraps",
  "view": "SEA-HELM leaderboard, 58 models, Indonesian (ID)",
  "rank": null,
  "rank_population": null,
  "date": "2026-09-18",
  "uncertainty": "95% CI [-1.27, +1.29]",
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://leaderboard.sea-lion.ai/detailed/ID"
  ]
 },
 {
  "model": "google-gemma-4-26b-a4b",
  "benchmark": "sea-helm",
  "score": 74.81,
  "unit": "score",
  "provenance": "maintainer-run",
  "setting": "Checkpoint gemma-4-26B-A4B-it as listed; release view (data last updated 18 Sep 2026); score is the average of 2000 bootstraps",
  "view": "SEA-HELM leaderboard, 58 models, SEA average",
  "rank": null,
  "rank_population": null,
  "date": "2026-09-18",
  "uncertainty": "95% CI [-0.59, +0.62]",
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://leaderboard.sea-lion.ai/detailed/SEA"
  ]
 },
 {
  "model": "google-gemma-4-26b-a4b",
  "benchmark": "sea-helm",
  "score": 78.26,
  "unit": "score",
  "provenance": "maintainer-run",
  "setting": "Checkpoint gemma-4-26B-A4B-it as listed; release view (data last updated 18 Sep 2026); score is the average of 2000 bootstraps",
  "view": "SEA-HELM leaderboard, 58 models, Indonesian (ID)",
  "rank": null,
  "rank_population": null,
  "date": "2026-09-18",
  "uncertainty": "95% CI [-1.29, +1.32]",
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://leaderboard.sea-lion.ai/detailed/ID"
  ]
 },
 {
  "model": "google-gemma-4-31b",
  "benchmark": "gpqa-diamond",
  "score": 84.3,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/google/gemma-4-31B-it",
   "https://huggingface.co/google"
  ]
 },
 {
  "model": "google-gemma-4-31b",
  "benchmark": "gpqa",
  "score": 84.3,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "Reported as 'GPQA' by secondary source; subset not stated",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2026-04",
  "sources": [
   "https://datanorth.ai/news/google-releases-gemma-4-open-models",
   "https://www.mindstudio.ai/blog/gemma-4-e2b-e4b-edge-models-phone-local"
  ],
  "unverified": []
 },
 {
  "model": "google-gemma-4-31b",
  "benchmark": "mmlu-pro",
  "score": 85.2,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2026-04",
  "sources": [
   "https://huggingface.co/google/gemma-4-31B-it",
   "https://huggingface.co/google",
   "https://datanorth.ai/news/google-releases-gemma-4-open-models",
   "https://www.mindstudio.ai/blog/gemma-4-e2b-e4b-edge-models-phone-local"
  ],
  "unverified": []
 },
 {
  "model": "google-gemma-4-31b",
  "benchmark": "sea-helm",
  "score": 76.17,
  "unit": "score",
  "provenance": "maintainer-run",
  "setting": null,
  "view": "SEA-HELM SEA average, open-weight models",
  "rank": 1,
  "rank_population": null,
  "date": "2026-09-18",
  "sources": [
   "https://leaderboard.sea-lion.ai/detailed/SEA"
  ],
  "uncertainty": "95% CI [-0.60, +0.59]"
 },
 {
  "model": "google-gemma-4-31b",
  "benchmark": "sea-helm",
  "score": 79.75,
  "unit": "index",
  "provenance": "maintainer-run",
  "setting": "Indonesian",
  "view": "SEA-HELM Indonesian",
  "rank": 1,
  "rank_population": null,
  "date": "2026-09-18",
  "sources": [
   "https://leaderboard.sea-lion.ai/detailed/ID"
  ],
  "unverified": [],
  "uncertainty": "95% CI [-1.25, +1.20]"
 },
 {
  "model": "google-gemma-4-31b",
  "benchmark": "sea-helm",
  "score": 79.75,
  "unit": "score",
  "provenance": "maintainer-run",
  "setting": null,
  "view": "SEA-HELM Indonesian, open-weight models, average of 2,000 bootstraps",
  "rank": 1,
  "rank_population": null,
  "date": "2026-09-18",
  "sources": [
   "https://leaderboard.sea-lion.ai/detailed/ID"
  ],
  "uncertainty": "95% CI [-1.25, +1.20]"
 },
 {
  "model": "google-gemma-4-e2b",
  "benchmark": "sea-helm",
  "score": 58.82,
  "unit": "score",
  "provenance": "maintainer-run",
  "setting": null,
  "view": "SEA-HELM SEA average, open-weight models",
  "rank": null,
  "rank_population": null,
  "date": "2026-09-18",
  "sources": [
   "https://leaderboard.sea-lion.ai/detailed/SEA"
  ],
  "uncertainty": "95% CI [-0.64, +0.66]"
 },
 {
  "model": "google-gemma-4-e2b",
  "benchmark": "sea-helm",
  "score": 64.13,
  "unit": "score",
  "provenance": "maintainer-run",
  "setting": null,
  "view": "SEA-HELM Indonesian, open-weight models, average of 2,000 bootstraps",
  "rank": null,
  "rank_population": null,
  "date": "2026-09-18",
  "sources": [
   "https://leaderboard.sea-lion.ai/detailed/ID"
  ],
  "uncertainty": "95% CI [-1.39, +1.41]"
 },
 {
  "model": "google-gemma-4-e4b",
  "benchmark": "sea-helm",
  "score": 66.3,
  "unit": "score",
  "provenance": "maintainer-run",
  "setting": "Checkpoint gemma-4-E4B-it as listed; release view (data last updated 18 Sep 2026); score is the average of 2000 bootstraps",
  "view": "SEA-HELM leaderboard, 58 models, SEA average",
  "rank": null,
  "rank_population": null,
  "date": "2026-09-18",
  "uncertainty": "95% CI [-0.65, +0.65]",
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://leaderboard.sea-lion.ai/detailed/SEA"
  ]
 },
 {
  "model": "google-gemma-4-e4b",
  "benchmark": "sea-helm",
  "score": 69.65,
  "unit": "score",
  "provenance": "maintainer-run",
  "setting": "Checkpoint gemma-4-E4B-it as listed; release view (data last updated 18 Sep 2026); score is the average of 2000 bootstraps",
  "view": "SEA-HELM leaderboard, 58 models, Indonesian (ID)",
  "rank": null,
  "rank_population": null,
  "date": "2026-09-18",
  "uncertainty": "95% CI [-1.40, +1.30]",
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://leaderboard.sea-lion.ai/detailed/ID"
  ]
 },
 {
  "model": "google-med-palm-2",
  "benchmark": "medqa",
  "score": 86.5,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2023",
  "sources": [
   "https://blog.google/innovation-and-ai/models-and-research/google-research/amie-video-consultations/"
  ],
  "unverified": [
   "score",
   "date"
  ]
 },
 {
  "model": "google-medgemma-27b-text",
  "benchmark": "afrimed-qa",
  "score": 84,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2025-07",
  "sources": [
   "https://arxiv.org/html/2507.05201v2",
   "https://huggingface.co/google/medgemma-27b-text-it"
  ]
 },
 {
  "model": "google-medgemma-27b-text",
  "benchmark": "agentclinic-medqa",
  "score": 56.2,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2025-07",
  "sources": [
   "https://arxiv.org/html/2507.05201v2",
   "https://huggingface.co/google/medgemma-27b-text-it"
  ]
 },
 {
  "model": "google-medgemma-27b-text",
  "benchmark": "medmcqa",
  "score": 74.2,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2025-07",
  "sources": [
   "https://arxiv.org/html/2507.05201v2",
   "https://huggingface.co/google/medgemma-27b-text-it"
  ]
 },
 {
  "model": "google-medgemma-27b-text",
  "benchmark": "medqa",
  "score": 87.7,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "27B, 0-shot with test-time scaling",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2025-07",
  "sources": [
   "https://arxiv.org/html/2507.05201v2",
   "https://huggingface.co/google/medgemma-27b-text-it"
  ]
 },
 {
  "model": "google-medgemma-27b-text",
  "benchmark": "medqa",
  "score": 89.8,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "27B, best-of-5",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2025-07",
  "sources": [
   "https://arxiv.org/html/2507.05201v2",
   "https://huggingface.co/google/medgemma-27b-text-it"
  ]
 },
 {
  "model": "google-medgemma-27b-text",
  "benchmark": "mmlu-med",
  "score": 87,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2025-07",
  "sources": [
   "https://arxiv.org/html/2507.05201v2",
   "https://huggingface.co/google/medgemma-27b-text-it"
  ]
 },
 {
  "model": "google-medgemma-27b-text",
  "benchmark": "pubmedqa",
  "score": 76.8,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2025-07",
  "sources": [
   "https://arxiv.org/html/2507.05201v2",
   "https://huggingface.co/google/medgemma-27b-text-it"
  ]
 },
 {
  "model": "google-medgemma-4b",
  "benchmark": "chexpert",
  "score": 48.1,
  "unit": "macro F1",
  "provenance": "vendor-reported",
  "setting": "Out of distribution",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2025-07",
  "sources": [
   "https://arxiv.org/html/2507.05201v2"
  ]
 },
 {
  "model": "google-medgemma-4b",
  "benchmark": "medqa",
  "score": 64.4,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2025-07",
  "sources": [
   "https://arxiv.org/html/2507.05201v2",
   "https://huggingface.co/google/medgemma-27b-text-it"
  ]
 },
 {
  "model": "google-medgemma-4b",
  "benchmark": "mimic-cxr",
  "score": 88.9,
  "unit": "macro F1",
  "provenance": "vendor-reported",
  "setting": "Med-Gemini test split",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2025-07",
  "sources": [
   "https://arxiv.org/html/2507.05201v2"
  ]
 },
 {
  "model": "google-medgemma-4b",
  "benchmark": "radgraph-f1",
  "score": 30.3,
  "unit": "F1",
  "provenance": "vendor-reported",
  "setting": "Fine-tuned",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2025-07",
  "sources": [
   "https://arxiv.org/html/2507.05201v2"
  ]
 },
 {
  "model": "google-nano-banana-2-lite",
  "benchmark": "aa-image-t2i-v2-0",
  "score": 1095,
  "unit": "Elo",
  "provenance": "independent",
  "setting": "rank shown as 13-16",
  "view": "AA Text-to-Image Arena, overall",
  "rank": 13,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://artificialanalysis.ai/text-to-image/arena/leaderboard-text"
  ]
 },
 {
  "model": "google-nano-banana-2",
  "benchmark": "aa-image-t2i-v2-0",
  "score": 1127,
  "unit": "Elo",
  "provenance": "independent",
  "setting": null,
  "view": "AA Text-to-Image Arena, overall",
  "rank": 7,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://artificialanalysis.ai/text-to-image/arena/leaderboard-text"
  ]
 },
 {
  "model": "google-nano-banana-2",
  "benchmark": "qwen-image-bench",
  "score": 59.82,
  "unit": "score",
  "provenance": "vendor-reported",
  "setting": "Qwen chart only; methodology unreleased",
  "view": "Qwen vendor chart",
  "rank": null,
  "rank_population": null,
  "date": "2026-09",
  "sources": [
   "https://datanorth.ai/news/qwen-releases-qwen-image-2-1"
  ]
 },
 {
  "model": "google-nano-banana-pro",
  "benchmark": "lmarena-text-to-image",
  "score": 1248,
  "unit": "Elo",
  "provenance": "independent",
  "setting": "gemini-3-pro-image-2k",
  "view": "LMArena Text-to-Image, overall, updated 7 Oct 2026",
  "rank": 16,
  "rank_population": null,
  "date": "2026-10-07",
  "sources": [
   "https://arena.ai/leaderboard/text-to-image"
  ],
  "uncertainty": "±3"
 },
 {
  "model": "google-stride-w-synapse",
  "benchmark": "gift-eval",
  "score": 0.423,
  "unit": "CRPS (geo-mean, normalised to Seasonal Naive)",
  "provenance": "independent",
  "setting": "agentic; rank is average CRPS rank",
  "view": "Leaderboard rebuilt from the published raw results, 143 entries covering all 97 configurations",
  "rank": 1,
  "rank_population": 143,
  "date": "2026-10-09",
  "sources": [
   "https://huggingface.co/spaces/Salesforce/GIFT-Eval"
  ],
  "leakage": "no",
  "leakage_note": "Test Leak. column: No (STRIDE w/ Synapse)"
 },
 {
  "model": "google-stride-w-synapse",
  "benchmark": "gift-eval",
  "score": 0.625,
  "unit": "MASE (geo-mean, normalised to Seasonal Naive)",
  "provenance": "independent",
  "setting": "agentic",
  "view": "Leaderboard rebuilt from the published raw results, 143 entries covering all 97 configurations",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-09",
  "sources": [
   "https://huggingface.co/spaces/Salesforce/GIFT-Eval"
  ],
  "leakage": "no",
  "leakage_note": "Test Leak. column: No (STRIDE w/ Synapse)"
 },
 {
  "model": "google-timesfm-2-5",
  "benchmark": "gift-eval",
  "score": 0.49,
  "unit": "CRPS (geo-mean, normalised to Seasonal Naive)",
  "provenance": "independent",
  "setting": "zero-shot; rank is average CRPS rank",
  "view": "Leaderboard rebuilt from the published raw results, 143 entries covering all 97 configurations",
  "rank": 66,
  "rank_population": 143,
  "date": "2026-10-09",
  "sources": [
   "https://huggingface.co/spaces/Salesforce/GIFT-Eval"
  ],
  "leakage": "no",
  "leakage_note": "Test Leak. column: No (TimesFM-2.5 (code))"
 },
 {
  "model": "google-timesfm-2-5",
  "benchmark": "gift-eval",
  "score": 0.705,
  "unit": "MASE (geo-mean, normalised to Seasonal Naive)",
  "provenance": "independent",
  "setting": "zero-shot",
  "view": "Leaderboard rebuilt from the published raw results, 143 entries covering all 97 configurations",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-09",
  "sources": [
   "https://huggingface.co/spaces/Salesforce/GIFT-Eval"
  ],
  "leakage": "no",
  "leakage_note": "Test Leak. column: No (TimesFM-2.5 (code))"
 },
 {
  "model": "google-timesfm-2-5",
  "benchmark": "gift-eval",
  "score": 25.8,
  "unit": "mean CRPS rank",
  "provenance": "vendor-reported",
  "setting": "zero-shot foundation-model CRPS rank, lower is better",
  "view": "Toto 2.0 report (Datadog)",
  "rank": null,
  "rank_population": null,
  "date": "2026-06",
  "sources": [
   "https://arxiv.org/pdf/2605.20119"
  ]
 },
 {
  "model": "google-timesfm-3-0",
  "benchmark": "gift-eval",
  "score": 0.456,
  "unit": "CRPS (geo-mean, normalised to Seasonal Naive)",
  "provenance": "independent",
  "setting": "zero-shot; rank is average CRPS rank",
  "view": "Leaderboard rebuilt from the published raw results, 143 entries covering all 97 configurations",
  "rank": 14,
  "rank_population": 143,
  "date": "2026-10-09",
  "sources": [
   "https://huggingface.co/spaces/Salesforce/GIFT-Eval"
  ],
  "leakage": "no",
  "leakage_note": "Test Leak. column: No (TimesFM-3 (code))"
 },
 {
  "model": "google-timesfm-3-0",
  "benchmark": "gift-eval",
  "score": 0.667,
  "unit": "MASE (geo-mean, normalised to Seasonal Naive)",
  "provenance": "independent",
  "setting": "zero-shot",
  "view": "Leaderboard rebuilt from the published raw results, 143 entries covering all 97 configurations",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-09",
  "sources": [
   "https://huggingface.co/spaces/Salesforce/GIFT-Eval"
  ],
  "leakage": "no",
  "leakage_note": "Test Leak. column: No (TimesFM-3 (code))"
 },
 {
  "model": "google-timesfm-3-0",
  "benchmark": "fev-bench",
  "score": null,
  "unit": null,
  "provenance": "vendor-reported",
  "setting": "Google claims best pretrained FM; no numbers given",
  "view": null,
  "rank": 1,
  "rank_population": null,
  "date": "2026-08-31",
  "sources": [
   "https://datanorth.ai/nl/nieuws/google-lanceert-timesfm-3"
  ]
 },
 {
  "model": "google-timesfm-3-0",
  "benchmark": "gift-eval",
  "score": null,
  "unit": null,
  "provenance": "vendor-reported",
  "setting": "Google claims best pretrained FM; no numbers given",
  "view": null,
  "rank": 1,
  "rank_population": null,
  "date": "2026-08-31",
  "sources": [
   "https://datanorth.ai/nl/nieuws/google-lanceert-timesfm-3"
  ]
 },
 {
  "model": "google-timesfm-3-0",
  "benchmark": "time",
  "score": null,
  "unit": null,
  "provenance": "vendor-reported",
  "setting": "Google claims best pretrained FM; no numbers given",
  "view": null,
  "rank": 1,
  "rank_population": null,
  "date": "2026-08-31",
  "sources": [
   "https://datanorth.ai/nl/nieuws/google-lanceert-timesfm-3"
  ]
 },
 {
  "model": "harvard-university-nequip-oam-l",
  "benchmark": "matbench-discovery",
  "score": 0.166,
  "unit": "kSRME",
  "provenance": "maintainer-run",
  "setting": "lower is better",
  "view": "leaderboard fetched 2026-10-10",
  "rank": null,
  "rank_population": null,
  "date": "2025-09-08",
  "sources": [
   "https://matbench-discovery.materialsproject.org/"
  ]
 },
 {
  "model": "harvard-university-nequip-oam-l",
  "benchmark": "matbench-discovery",
  "score": 0.87,
  "unit": "CPS",
  "provenance": "maintainer-run",
  "setting": null,
  "view": "leaderboard fetched 2026-10-10, ranked by CPS",
  "rank": 7,
  "rank_population": null,
  "date": "2025-09-08",
  "sources": [
   "https://matbench-discovery.materialsproject.org/"
  ]
 },
 {
  "model": "harvard-university-nequip-oam-l",
  "benchmark": "matbench-discovery",
  "score": 0.893,
  "unit": "F1",
  "provenance": "maintainer-run",
  "setting": null,
  "view": "leaderboard fetched 2026-10-10",
  "rank": null,
  "rank_population": null,
  "date": "2025-09-08",
  "sources": [
   "https://matbench-discovery.materialsproject.org/"
  ]
 },
 {
  "model": "harvard-university-nequip-oam-xl",
  "benchmark": "matbench-discovery",
  "score": 0.125,
  "unit": "kSRME",
  "provenance": "maintainer-run",
  "setting": "lower is better",
  "view": "leaderboard fetched 2026-10-10",
  "rank": null,
  "rank_population": null,
  "date": "2025-11-30",
  "sources": [
   "https://matbench-discovery.materialsproject.org/"
  ]
 },
 {
  "model": "harvard-university-nequip-oam-xl",
  "benchmark": "matbench-discovery",
  "score": 0.886,
  "unit": "CPS",
  "provenance": "maintainer-run",
  "setting": null,
  "view": "leaderboard fetched 2026-10-10, ranked by CPS",
  "rank": 4,
  "rank_population": null,
  "date": "2025-11-30",
  "sources": [
   "https://matbench-discovery.materialsproject.org/"
  ]
 },
 {
  "model": "harvard-university-nequip-oam-xl",
  "benchmark": "matbench-discovery",
  "score": 0.906,
  "unit": "F1",
  "provenance": "maintainer-run",
  "setting": null,
  "view": "leaderboard fetched 2026-10-10",
  "rank": null,
  "rank_population": null,
  "date": "2025-11-30",
  "sources": [
   "https://matbench-discovery.materialsproject.org/"
  ]
 },
 {
  "model": "hidream-ai-hidream-i1-dev",
  "benchmark": "aa-image-t2i-v2-0",
  "score": 874,
  "unit": "Elo",
  "provenance": "independent",
  "setting": "approximate rank",
  "view": "AA Text-to-Image Arena, overall",
  "rank": 120,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://artificialanalysis.ai/text-to-image/arena/leaderboard-text"
  ]
 },
 {
  "model": "hidream-ai-hidream-o1-image-1-5",
  "benchmark": "aa-image-t2i-v2-0",
  "score": 1019,
  "unit": "Elo",
  "provenance": "independent",
  "setting": "approximate rank",
  "view": "AA Text-to-Image Arena, overall",
  "rank": 31,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://artificialanalysis.ai/text-to-image/arena/leaderboard-text"
  ]
 },
 {
  "model": "hidream-ai-hidream-o1-video",
  "benchmark": "vbench",
  "score": 89.43,
  "unit": "%",
  "provenance": "maintainer-run",
  "setting": "Quality score; submission-based board",
  "view": "VBench (v1) text-to-video",
  "rank": null,
  "rank_population": null,
  "date": "2026-08-07",
  "sources": [
   "https://huggingface.co/spaces/Vchitect/VBench_Leaderboard"
  ]
 },
 {
  "model": "hidream-ai-hidream-o1-video",
  "benchmark": "vbench",
  "score": 89.74,
  "unit": "%",
  "provenance": "maintainer-run",
  "setting": "Total score; submission-based board",
  "view": "VBench (v1) text-to-video",
  "rank": 1,
  "rank_population": null,
  "date": "2026-08-07",
  "sources": [
   "https://huggingface.co/spaces/Vchitect/VBench_Leaderboard"
  ]
 },
 {
  "model": "huawei-pangu-weather",
  "benchmark": "weatherbench-2",
  "score": 1.766,
  "unit": "RMSE K",
  "provenance": "maintainer-run",
  "setting": "T850 day 5, deterministic, Pangu-Weather (oper.) vs Analysis",
  "view": "year 2022, 240x121 grid",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://researchsites.withgoogle.com/weatherbench/deterministic/"
  ]
 },
 {
  "model": "huawei-pangu-weather",
  "benchmark": "weatherbench-2",
  "score": 133.8,
  "unit": "RMSE m2/s2",
  "provenance": "maintainer-run",
  "setting": "Z500 day 3, deterministic, Pangu-Weather vs ERA5",
  "view": "year 2020, 240x121 grid",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://researchsites.withgoogle.com/weatherbench/deterministic/"
  ]
 },
 {
  "model": "huawei-pangu-weather",
  "benchmark": "weatherbench-2",
  "score": 138.4,
  "unit": "RMSE m2/s2",
  "provenance": "maintainer-run",
  "setting": "Z500 day 3, deterministic, Pangu-Weather (oper.) vs Analysis",
  "view": "year 2022, 240x121 grid",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://researchsites.withgoogle.com/weatherbench/deterministic/"
  ]
 },
 {
  "model": "huawei-pangu-weather",
  "benchmark": "weatherbench-2",
  "score": 294.3,
  "unit": "RMSE m2/s2",
  "provenance": "maintainer-run",
  "setting": "Z500 day 5, deterministic, Pangu-Weather vs ERA5",
  "view": "year 2020, 240x121 grid",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://researchsites.withgoogle.com/weatherbench/deterministic/"
  ]
 },
 {
  "model": "huawei-pangu-weather",
  "benchmark": "weatherbench-2",
  "score": 3.573,
  "unit": "RMSE K",
  "provenance": "maintainer-run",
  "setting": "T850 day 10, deterministic, Pangu-Weather (oper.) vs Analysis",
  "view": "year 2022, 240x121 grid",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://researchsites.withgoogle.com/weatherbench/deterministic/"
  ]
 },
 {
  "model": "huawei-pangu-weather",
  "benchmark": "weatherbench-2",
  "score": 304.4,
  "unit": "RMSE m2/s2",
  "provenance": "maintainer-run",
  "setting": "Z500 day 5, deterministic, Pangu-Weather (oper.) vs Analysis",
  "view": "year 2022, 240x121 grid",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://researchsites.withgoogle.com/weatherbench/deterministic/"
  ]
 },
 {
  "model": "huawei-pangu-weather",
  "benchmark": "weatherbench-2",
  "score": 44.3,
  "unit": "RMSE m2/s2",
  "provenance": "maintainer-run",
  "setting": "Z500 day 1, deterministic, Pangu-Weather vs ERA5",
  "view": "year 2020, 240x121 grid",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://researchsites.withgoogle.com/weatherbench/deterministic/"
  ]
 },
 {
  "model": "huawei-pangu-weather",
  "benchmark": "weatherbench-2",
  "score": 45,
  "unit": "RMSE m2/s2",
  "provenance": "maintainer-run",
  "setting": "Z500 day 1, deterministic, Pangu-Weather (oper.) vs Analysis",
  "view": "year 2022, 240x121 grid",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://researchsites.withgoogle.com/weatherbench/deterministic/"
  ]
 },
 {
  "model": "huawei-pangu-weather",
  "benchmark": "weatherbench-2",
  "score": 778.2,
  "unit": "RMSE m2/s2",
  "provenance": "maintainer-run",
  "setting": "Z500 day 10, deterministic, Pangu-Weather vs ERA5",
  "view": "year 2020, 240x121 grid",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://researchsites.withgoogle.com/weatherbench/deterministic/"
  ]
 },
 {
  "model": "huawei-pangu-weather",
  "benchmark": "weatherbench-2",
  "score": 799.8,
  "unit": "RMSE m2/s2",
  "provenance": "maintainer-run",
  "setting": "Z500 day 10, deterministic, Pangu-Weather (oper.) vs Analysis",
  "view": "year 2022, 240x121 grid",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://researchsites.withgoogle.com/weatherbench/deterministic/"
  ]
 },
 {
  "model": "hugging-face-smollm3-3b",
  "benchmark": "aime-2025",
  "score": 36.7,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "Card 3-model comparison table; mode label not extracted",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/HuggingFaceTB/SmolLM3-3B"
  ],
  "unverified": []
 },
 {
  "model": "hugging-face-smollm3-3b",
  "benchmark": "aime-2025",
  "score": 9.3,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "Card 5-model comparison table; mode label not extracted",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/HuggingFaceTB/SmolLM3-3B"
  ],
  "unverified": []
 },
 {
  "model": "hugging-face-smollm3-3b",
  "benchmark": "bfcl",
  "score": 92.3,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "Card 5-model comparison table; mode label not extracted",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/HuggingFaceTB/SmolLM3-3B"
  ],
  "unverified": []
 },
 {
  "model": "hugging-face-smollm3-3b",
  "benchmark": "global-mmlu",
  "score": 53.5,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "Card 5-model comparison table; mode label not extracted",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/HuggingFaceTB/SmolLM3-3B"
  ],
  "unverified": []
 },
 {
  "model": "hugging-face-smollm3-3b",
  "benchmark": "gpqa-diamond",
  "score": 35.7,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "Card 5-model comparison table; mode label not extracted",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/HuggingFaceTB/SmolLM3-3B"
  ],
  "unverified": []
 },
 {
  "model": "hugging-face-smollm3-3b",
  "benchmark": "ifeval",
  "score": 76.7,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "Card 5-model comparison table; mode label not extracted",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/HuggingFaceTB/SmolLM3-3B"
  ],
  "unverified": []
 },
 {
  "model": "ibm-flowstate-r1-1",
  "benchmark": "gift-eval",
  "score": 0.487,
  "unit": "CRPS (geo-mean, normalised to Seasonal Naive)",
  "provenance": "independent",
  "setting": "zero-shot; rank is average CRPS rank",
  "view": "Leaderboard rebuilt from the published raw results, 143 entries covering all 97 configurations",
  "rank": 64,
  "rank_population": 143,
  "date": "2026-10-09",
  "sources": [
   "https://huggingface.co/spaces/Salesforce/GIFT-Eval"
  ],
  "leakage": "no",
  "leakage_note": "Test Leak. column: No (FlowState-r1.1 (code))"
 },
 {
  "model": "ibm-flowstate-r1-1",
  "benchmark": "gift-eval",
  "score": 0.701,
  "unit": "MASE (geo-mean, normalised to Seasonal Naive)",
  "provenance": "independent",
  "setting": "zero-shot",
  "view": "Leaderboard rebuilt from the published raw results, 143 entries covering all 97 configurations",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-09",
  "sources": [
   "https://huggingface.co/spaces/Salesforce/GIFT-Eval"
  ],
  "leakage": "no",
  "leakage_note": "Test Leak. column: No (FlowState-r1.1 (code))"
 },
 {
  "model": "ibm-flowstate-r1-1",
  "benchmark": "gift-eval",
  "score": 25.6,
  "unit": "mean CRPS rank",
  "provenance": "vendor-reported",
  "setting": "zero-shot foundation-model CRPS rank, lower is better",
  "view": "Toto 2.0 report (Datadog)",
  "rank": null,
  "rank_population": null,
  "date": "2026-06",
  "sources": [
   "https://arxiv.org/pdf/2605.20119"
  ]
 },
 {
  "model": "ibm-granite-4-0-1b-speech",
  "benchmark": "open-asr-leaderboard",
  "score": 5.52,
  "unit": "WER",
  "provenance": "maintainer-run",
  "setting": "eight-set macro-average English WER",
  "view": "snapshot 2026-05-06 via benchmarklist",
  "rank": null,
  "rank_population": null,
  "date": "2026-05-06",
  "sources": [
   "https://benchmarklist.com/benchmarks/open_asr_leaderboard/"
  ]
 },
 {
  "model": "ibm-granite-4-0-h-micro",
  "benchmark": "bfcl",
  "score": 57.56,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "BFCL v3",
  "view": "Granite-4.0-H-Micro model card",
  "rank": null,
  "rank_population": null,
  "date": "2025-10-02",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://huggingface.co/ibm-granite/granite-4.0-h-micro"
  ]
 },
 {
  "model": "ibm-granite-4-0-h-micro",
  "benchmark": "gpqa",
  "score": 32.15,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "0-shot, CoT",
  "view": "Granite-4.0-H-Micro model card",
  "rank": null,
  "rank_population": null,
  "date": "2025-10-02",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://huggingface.co/ibm-granite/granite-4.0-h-micro"
  ]
 },
 {
  "model": "ibm-granite-4-0-h-micro",
  "benchmark": "gsm8k",
  "score": 81.35,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "8-shot",
  "view": "Granite-4.0-H-Micro model card",
  "rank": null,
  "rank_population": null,
  "date": "2025-10-02",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://huggingface.co/ibm-granite/granite-4.0-h-micro"
  ]
 },
 {
  "model": "ibm-granite-4-0-h-micro",
  "benchmark": "humaneval",
  "score": 81,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "pass@1",
  "view": "Granite-4.0-H-Micro model card",
  "rank": null,
  "rank_population": null,
  "date": "2025-10-02",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://huggingface.co/ibm-granite/granite-4.0-h-micro"
  ]
 },
 {
  "model": "ibm-granite-4-0-h-micro",
  "benchmark": "ifeval",
  "score": 84.32,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "Average of instruct and prompt strict",
  "view": "Granite-4.0-H-Micro model card",
  "rank": null,
  "rank_population": null,
  "date": "2025-10-02",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://huggingface.co/ibm-granite/granite-4.0-h-micro"
  ]
 },
 {
  "model": "ibm-granite-4-0-h-micro",
  "benchmark": "mmlu-pro",
  "score": 43.48,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "5-shot, CoT",
  "view": "Granite-4.0-H-Micro model card",
  "rank": null,
  "rank_population": null,
  "date": "2025-10-02",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://huggingface.co/ibm-granite/granite-4.0-h-micro"
  ]
 },
 {
  "model": "ibm-granite-4-0-h-micro",
  "benchmark": "mmlu",
  "score": 67.43,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "5-shot",
  "view": "Granite-4.0-H-Micro model card",
  "rank": null,
  "rank_population": null,
  "date": "2025-10-02",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://huggingface.co/ibm-granite/granite-4.0-h-micro"
  ]
 },
 {
  "model": "ibm-granite-4-2-8b",
  "benchmark": "ifbench",
  "score": 79.33,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/ibm-granite/granite-4.2-8b"
  ]
 },
 {
  "model": "ibm-granite-4-2-8b",
  "benchmark": "mmlu-pro",
  "score": 74.04,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/ibm-granite/granite-4.2-8b"
  ]
 },
 {
  "model": "ibm-granite-4-2-8b",
  "benchmark": "swe-bench-verified",
  "score": 47.67,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/ibm-granite/granite-4.2-8b"
  ]
 },
 {
  "model": "ibm-granite-flowstate",
  "benchmark": "gift-eval",
  "score": null,
  "unit": null,
  "provenance": "vendor-reported",
  "setting": "IBM Granite docs",
  "view": null,
  "rank": 3,
  "rank_population": null,
  "date": "2025-10-02",
  "sources": [
   "https://www.ibm.com/ae-ar/granite/docs/models/time-series/"
  ]
 },
 {
  "model": "ibm-granite-guardian-4-1-8b",
  "benchmark": "fc-reward-bench",
  "score": 0.79,
  "unit": "F1",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/ibm-granite/granite-guardian-4.1-8b"
  ]
 },
 {
  "model": "ibm-granite-guardian-4-1-8b",
  "benchmark": "granite-guardian-ood-safety",
  "score": 0.79,
  "unit": "F1",
  "provenance": "vendor-reported",
  "setting": "out-of-distribution safety",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/ibm-granite/granite-guardian-4.1-8b"
  ]
 },
 {
  "model": "ibm-granite-guardian-4-1-8b",
  "benchmark": "lm-aggrefact",
  "score": 0.76,
  "unit": "F1",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/ibm-granite/granite-guardian-4.1-8b"
  ]
 },
 {
  "model": "ibm-granite-patchtst-fm-r1",
  "benchmark": "gift-eval",
  "score": 23.1,
  "unit": "mean CRPS rank",
  "provenance": "vendor-reported",
  "setting": "zero-shot foundation-model CRPS rank, lower is better",
  "view": "Toto 2.0 report (Datadog)",
  "rank": null,
  "rank_population": null,
  "date": "2026-06",
  "sources": [
   "https://arxiv.org/pdf/2605.20119"
  ]
 },
 {
  "model": "ibm-granite-patchtst-fm-r2",
  "benchmark": "gift-eval",
  "score": 0.467,
  "unit": "CRPS (geo-mean, normalised to Seasonal Naive)",
  "provenance": "independent",
  "setting": "zero-shot; rank is average CRPS rank",
  "view": "Leaderboard rebuilt from the published raw results, 143 entries covering all 97 configurations",
  "rank": 36,
  "rank_population": 143,
  "date": "2026-10-09",
  "sources": [
   "https://huggingface.co/spaces/Salesforce/GIFT-Eval"
  ],
  "leakage": "no",
  "leakage_note": "Test Leak. column: No (Granite-PatchTST-FM-r2 (code))"
 },
 {
  "model": "ibm-granite-patchtst-fm-r2",
  "benchmark": "gift-eval",
  "score": 0.685,
  "unit": "MASE (geo-mean, normalised to Seasonal Naive)",
  "provenance": "independent",
  "setting": "zero-shot",
  "view": "Leaderboard rebuilt from the published raw results, 143 entries covering all 97 configurations",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-09",
  "sources": [
   "https://huggingface.co/spaces/Salesforce/GIFT-Eval"
  ],
  "leakage": "no",
  "leakage_note": "Test Leak. column: No (Granite-PatchTST-FM-r2 (code))"
 },
 {
  "model": "ibm-granite-speech-3-3-8b",
  "benchmark": "open-asr-leaderboard",
  "score": 5.74,
  "unit": "WER",
  "provenance": "maintainer-run",
  "setting": "eight-set macro-average English WER",
  "view": "snapshot 2026-05-06 via benchmarklist",
  "rank": null,
  "rank_population": null,
  "date": "2026-05-06",
  "sources": [
   "https://benchmarklist.com/benchmarks/open_asr_leaderboard/"
  ]
 },
 {
  "model": "ibm-granite-speech-4-1-2b",
  "benchmark": "open-asr-leaderboard",
  "score": 5.33,
  "unit": "WER",
  "provenance": "maintainer-run",
  "setting": "eight-set macro-average English WER",
  "view": "snapshot 2026-05-06 via benchmarklist",
  "rank": 1,
  "rank_population": null,
  "date": "2026-05-06",
  "sources": [
   "https://benchmarklist.com/benchmarks/open_asr_leaderboard/"
  ]
 },
 {
  "model": "ibm-granite-tspulse",
  "benchmark": "tsb-ad",
  "score": null,
  "unit": "VUS-PR",
  "provenance": "vendor-reported",
  "setting": "IBM claims #1 on univariate and multivariate, +20%; no scores published on card; conflicts with PaAno rank 1",
  "view": null,
  "rank": 1,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/ibm-granite/granite-timeseries-tspulse-r1"
  ]
 },
 {
  "model": "ibm-granite-ttm-r2",
  "benchmark": "gift-eval",
  "score": 0.873,
  "unit": "CRPS (geo-mean, normalised to Seasonal Naive)",
  "provenance": "independent",
  "setting": "pretrained, test leakage Yes; rank is average CRPS rank",
  "view": "Leaderboard rebuilt from the published raw results, 143 entries covering all 97 configurations",
  "rank": 140,
  "rank_population": 143,
  "date": "2026-10-09",
  "sources": [
   "https://huggingface.co/spaces/Salesforce/GIFT-Eval"
  ],
  "leakage": "yes",
  "leakage_note": "Test Leak. column: Yes (TTM-R2-Pretrained (code))"
 },
 {
  "model": "ibm-granite-ttm-r2",
  "benchmark": "gift-eval",
  "score": 1.02,
  "unit": "MASE (geo-mean, normalised to Seasonal Naive)",
  "provenance": "independent",
  "setting": "pretrained, test leakage Yes",
  "view": "Leaderboard rebuilt from the published raw results, 143 entries covering all 97 configurations",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-09",
  "sources": [
   "https://huggingface.co/spaces/Salesforce/GIFT-Eval"
  ],
  "leakage": "yes",
  "leakage_note": "Test Leak. column: Yes (TTM-R2-Pretrained (code))"
 },
 {
  "model": "icams-bochum-grace-2l-oam-l",
  "benchmark": "matbench-discovery",
  "score": 0.169,
  "unit": "kSRME",
  "provenance": "maintainer-run",
  "setting": "lower is better",
  "view": "leaderboard fetched 2026-10-10",
  "rank": null,
  "rank_population": null,
  "date": "2025-09-09",
  "sources": [
   "https://matbench-discovery.materialsproject.org/"
  ]
 },
 {
  "model": "icams-bochum-grace-2l-oam-l",
  "benchmark": "matbench-discovery",
  "score": 0.865,
  "unit": "CPS",
  "provenance": "maintainer-run",
  "setting": null,
  "view": "leaderboard fetched 2026-10-10, ranked by CPS",
  "rank": 9,
  "rank_population": null,
  "date": "2025-09-09",
  "sources": [
   "https://matbench-discovery.materialsproject.org/"
  ]
 },
 {
  "model": "icams-bochum-grace-2l-oam-l",
  "benchmark": "matbench-discovery",
  "score": 0.883,
  "unit": "F1",
  "provenance": "maintainer-run",
  "setting": null,
  "view": "leaderboard fetched 2026-10-10",
  "rank": null,
  "rank_population": null,
  "date": "2025-09-09",
  "sources": [
   "https://matbench-discovery.materialsproject.org/"
  ]
 },
 {
  "model": "ideogram-4-0",
  "benchmark": "aa-image-t2i-v2-0",
  "score": 1003,
  "unit": "Elo",
  "provenance": "independent",
  "setting": "approximate rank",
  "view": "AA Text-to-Image Arena, overall",
  "rank": 40,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://artificialanalysis.ai/text-to-image/arena/leaderboard-text"
  ]
 },
 {
  "model": "ideogram-4-0",
  "benchmark": "aa-image-t2i-v2-0",
  "score": 1012,
  "unit": "Elo",
  "provenance": "independent",
  "setting": "Quality mode; approximate rank",
  "view": "AA Text-to-Image Arena, overall",
  "rank": 38,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://artificialanalysis.ai/text-to-image/arena/leaderboard-text"
  ]
 },
 {
  "model": "ideogram-4-0",
  "benchmark": "lmarena-text-to-image",
  "score": 1205,
  "unit": "Elo",
  "provenance": "independent",
  "setting": "ideogram-4.0-quality",
  "view": "LMArena Text-to-Image, overall, updated 7 Oct 2026",
  "rank": 20,
  "rank_population": null,
  "date": "2026-10-07",
  "sources": [
   "https://arena.ai/leaderboard/text-to-image"
  ],
  "uncertainty": "±4"
 },
 {
  "model": "ideogram-v2",
  "benchmark": "aa-image-arena",
  "score": 884,
  "unit": "Elo",
  "provenance": "independent",
  "setting": "text-to-image, 7,815 samples",
  "view": "AA text-to-image leaderboard, 168 models",
  "rank": 113,
  "rank_population": 168,
  "date": "2026-10-11",
  "uncertainty": "+/-8 (95% interval 876 to 892); rank range 105 to 116",
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://artificialanalysis.ai/image/leaderboard/text-to-image"
  ]
 },
 {
  "model": "idsv-ft-whisper",
  "benchmark": "idsv",
  "score": 10.38,
  "unit": "WER",
  "provenance": "independent",
  "setting": "IDSV group RFC",
  "view": "Table 3, by speech variability",
  "rank": null,
  "rank_population": null,
  "date": "2024-10",
  "sources": [
   "https://arxiv.org/html/2410.08828v2"
  ]
 },
 {
  "model": "idsv-ft-whisper",
  "benchmark": "idsv",
  "score": 13.04,
  "unit": "WER",
  "provenance": "independent",
  "setting": "IDSV group SIM",
  "view": "Table 3, by speech variability",
  "rank": null,
  "rank_population": null,
  "date": "2024-10",
  "sources": [
   "https://arxiv.org/html/2410.08828v2"
  ]
 },
 {
  "model": "idsv-ft-whisper",
  "benchmark": "idsv",
  "score": 13.12,
  "unit": "WER",
  "provenance": "independent",
  "setting": "IDSV group RFM",
  "view": "Table 3, by speech variability",
  "rank": null,
  "rank_population": null,
  "date": "2024-10",
  "sources": [
   "https://arxiv.org/html/2410.08828v2"
  ]
 },
 {
  "model": "idsv-ft-whisper",
  "benchmark": "idsv",
  "score": 14.85,
  "unit": "WER",
  "provenance": "independent",
  "setting": "IDSV test, all groups",
  "view": "Table 3",
  "rank": null,
  "rank_population": null,
  "date": "2024-10",
  "sources": [
   "https://arxiv.org/html/2410.08828v2"
  ]
 },
 {
  "model": "idsv-ft-whisper",
  "benchmark": "idsv",
  "score": 15.98,
  "unit": "WER",
  "provenance": "independent",
  "setting": "IDSV group SFM",
  "view": "Table 3, by speech variability",
  "rank": null,
  "rank_population": null,
  "date": "2024-10",
  "sources": [
   "https://arxiv.org/html/2410.08828v2"
  ]
 },
 {
  "model": "idsv-ft-whisper",
  "benchmark": "idsv",
  "score": 29.64,
  "unit": "WER",
  "provenance": "independent",
  "setting": "IDSV group SIC",
  "view": "Table 3, by speech variability",
  "rank": null,
  "rank_population": null,
  "date": "2024-10",
  "sources": [
   "https://arxiv.org/html/2410.08828v2"
  ]
 },
 {
  "model": "idsv-ft-whisper",
  "benchmark": "idsv",
  "score": 5.44,
  "unit": "CER",
  "provenance": "independent",
  "setting": "IDSV test, all groups",
  "view": "Table 3",
  "rank": null,
  "rank_population": null,
  "date": "2024-10",
  "sources": [
   "https://arxiv.org/html/2410.08828v2"
  ]
 },
 {
  "model": "idsv-mms-ft-lm",
  "benchmark": "idsv",
  "score": 19.95,
  "unit": "WER",
  "provenance": "independent",
  "setting": "IDSV test, all",
  "view": "Table 3",
  "rank": null,
  "rank_population": null,
  "date": "2024-10",
  "sources": [
   "https://arxiv.org/html/2410.08828v2"
  ]
 },
 {
  "model": "idsv-mms-ft-lm",
  "benchmark": "idsv",
  "score": 6.45,
  "unit": "CER",
  "provenance": "independent",
  "setting": "IDSV test, all",
  "view": "Table 3",
  "rank": null,
  "rank_population": null,
  "date": "2024-10",
  "sources": [
   "https://arxiv.org/html/2410.08828v2"
  ]
 },
 {
  "model": "idsv-mms-ft",
  "benchmark": "idsv",
  "score": 29.66,
  "unit": "WER",
  "provenance": "independent",
  "setting": "IDSV test, all",
  "view": "Table 3",
  "rank": null,
  "rank_population": null,
  "date": "2024-10",
  "sources": [
   "https://arxiv.org/html/2410.08828v2"
  ]
 },
 {
  "model": "idsv-mms-ft",
  "benchmark": "idsv",
  "score": 7.86,
  "unit": "CER",
  "provenance": "independent",
  "setting": "IDSV test, all",
  "view": "Table 3",
  "rank": null,
  "rank_population": null,
  "date": "2024-10",
  "sources": [
   "https://arxiv.org/html/2410.08828v2"
  ]
 },
 {
  "model": "inclusionai-ling-1t",
  "benchmark": "aime-2025",
  "score": 70.42,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "Average over 4,000 output tokens per problem",
  "view": "Ant Group claim reported by AI News",
  "rank": null,
  "rank_population": null,
  "date": "2025-10",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://www.artificialintelligence-news.com/news/trillion-parameter-ai-model-ant-group-ling-1t/"
  ]
 },
 {
  "model": "inclusionai-ling-3-0-flash",
  "benchmark": "hle",
  "score": 22.7,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": "Ling-3.0-flash model card eval results",
  "rank": null,
  "rank_population": null,
  "date": "2026-07",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://huggingface.co/inclusionAI/Ling-3.0-flash"
  ]
 },
 {
  "model": "inclusionai-ling-3-0-flash",
  "benchmark": "swe-bench-multilingual",
  "score": 72.4,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": "Ling-3.0-flash model card eval results",
  "rank": null,
  "rank_population": null,
  "date": "2026-07",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://huggingface.co/inclusionAI/Ling-3.0-flash"
  ]
 },
 {
  "model": "inclusionai-ling-3-0-flash",
  "benchmark": "swe-bench-pro",
  "score": 56.6,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": "Ling-3.0-flash model card eval results",
  "rank": null,
  "rank_population": null,
  "date": "2026-07",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://huggingface.co/inclusionAI/Ling-3.0-flash"
  ]
 },
 {
  "model": "indonesian-nlp-wav2vec2-indonesian-javanese-sundanese",
  "benchmark": "common-voice-6-1",
  "score": 4.056,
  "unit": "WER",
  "provenance": "vendor-reported",
  "setting": "Indonesian test split; CER 1.472",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://huggingface.co/indonesian-nlp/wav2vec2-indonesian-javanese-sundanese"
  ]
 },
 {
  "model": "indonesian-nlp-wav2vec2-indonesian-javanese-sundanese",
  "benchmark": "common-voice-7",
  "score": 4.492,
  "unit": "WER",
  "provenance": "vendor-reported",
  "setting": "Indonesian test split; CER 1.577",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://huggingface.co/indonesian-nlp/wav2vec2-indonesian-javanese-sundanese"
  ]
 },
 {
  "model": "inria-tabicl-v2",
  "benchmark": "tabarena",
  "score": 1598,
  "unit": "Elo",
  "provenance": "maintainer-run",
  "setting": "default",
  "view": "All Tasks, no imputation, snapshot 2026-05-06, 59 entries",
  "rank": 4,
  "rank_population": 59,
  "date": "2026-05-06",
  "sources": [
   "https://benchmarklist.com/benchmarks/tabarena_all/",
   "https://benchmarklist.com/benchmarks/tabarena_all/"
  ]
 },
 {
  "model": "institute-of-foundation-models-k2-horizon-375b-a23b",
  "benchmark": "aa-intelligence-index",
  "score": 31,
  "unit": "index",
  "provenance": "independent",
  "setting": null,
  "view": "AA leaderboard, 205 current models",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://artificialanalysis.ai/leaderboards/models"
  ]
 },
 {
  "model": "internscience-agents-a1-4b",
  "benchmark": "gaia",
  "score": 95.1,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "Self-report; only BenchLM row, not marked current",
  "view": "BenchLM",
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://benchlm.ai/benchmarks/gaia"
  ],
  "unverified": []
 },
 {
  "model": "ipoc",
  "benchmark": "vbench",
  "score": 86.57,
  "unit": "%",
  "provenance": "maintainer-run",
  "setting": "Total score; submission-based board",
  "view": "VBench (v1) text-to-video",
  "rank": 4,
  "rank_population": null,
  "date": "2025-04-14",
  "sources": [
   "https://huggingface.co/spaces/Vchitect/VBench_Leaderboard"
  ]
 },
 {
  "model": "ipoc",
  "benchmark": "vbench",
  "score": 87,
  "unit": "%",
  "provenance": "maintainer-run",
  "setting": "Quality score; submission-based board",
  "view": "VBench (v1) text-to-video",
  "rank": null,
  "rank_population": null,
  "date": "2025-04-14",
  "sources": [
   "https://huggingface.co/spaces/Vchitect/VBench_Leaderboard"
  ]
 },
 {
  "model": "ipow",
  "benchmark": "vbench",
  "score": 87.83,
  "unit": "%",
  "provenance": "maintainer-run",
  "setting": "Quality score; submission-based board",
  "view": "VBench (v1) text-to-video",
  "rank": null,
  "rank_population": null,
  "date": "2025-08-06",
  "sources": [
   "https://huggingface.co/spaces/Vchitect/VBench_Leaderboard"
  ]
 },
 {
  "model": "ipow",
  "benchmark": "vbench",
  "score": 88.26,
  "unit": "%",
  "provenance": "maintainer-run",
  "setting": "Total score; submission-based board",
  "view": "VBench (v1) text-to-video",
  "rank": 2,
  "rank_population": null,
  "date": "2025-08-06",
  "sources": [
   "https://huggingface.co/spaces/Vchitect/VBench_Leaderboard"
  ]
 },
 {
  "model": "isolation-forest",
  "benchmark": "skab",
  "score": 26.16,
  "unit": "NAB score",
  "provenance": "maintainer-run",
  "setting": "Changepoint detection leaderboard",
  "view": null,
  "rank": 2,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://github.com/waico/SKAB"
  ]
 },
 {
  "model": "jetbrains-mellum2-1-12b-a2-5b-thinking",
  "benchmark": "humaneval-plus",
  "score": 91.5,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "thinking mode",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/JetBrains/Mellum2.1-12B-A2.5B-Thinking"
  ]
 },
 {
  "model": "jetbrains-mellum2-1-12b-a2-5b-thinking",
  "benchmark": "livecodebench",
  "score": 82,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "thinking mode, LiveCodeBench v6",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/JetBrains/Mellum2.1-12B-A2.5B-Thinking"
  ]
 },
 {
  "model": "jetbrains-mellum2-1-12b-a2-5b-thinking",
  "benchmark": "mbpp-plus",
  "score": 79.4,
  "unit": null,
  "provenance": "vendor-reported",
  "setting": "thinking mode",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/JetBrains/Mellum2.1-12B-A2.5B-Thinking"
  ]
 },
 {
  "model": "jetbrains-mellum2-1-12b-a2-5b-thinking",
  "benchmark": "swe-bench-pro",
  "score": 28,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "thinking mode",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/JetBrains/Mellum2.1-12B-A2.5B-Thinking"
  ]
 },
 {
  "model": "jetbrains-mellum2-1-12b-a2-5b-thinking",
  "benchmark": "swe-bench-verified",
  "score": 47,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "thinking mode",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/JetBrains/Mellum2.1-12B-A2.5B-Thinking"
  ]
 },
 {
  "model": "jetbrains-mellum2-1-12b-a2-5b-thinking",
  "benchmark": "terminal-bench-2-1",
  "score": 17.4,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "thinking mode",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/JetBrains/Mellum2.1-12B-A2.5B-Thinking"
  ]
 },
 {
  "model": "jina-ai-jina-embeddings-v5-text-small",
  "benchmark": "mmteb",
  "score": 67.7,
  "unit": "score",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/jinaai/jina-embeddings-v5-text-small"
  ]
 },
 {
  "model": "jina-ai-jina-embeddings-v5-text-small",
  "benchmark": "mteb-english-v2",
  "score": 71.7,
  "unit": "score",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/jinaai/jina-embeddings-v5-text-small"
  ]
 },
 {
  "model": "jt-cv",
  "benchmark": "vbench-2-0",
  "score": 51.8,
  "unit": "%",
  "provenance": "maintainer-run",
  "setting": "Creativity score",
  "view": "VBench-2.0",
  "rank": null,
  "rank_population": null,
  "date": "2026-04-01",
  "sources": [
   "https://huggingface.co/spaces/Vchitect/VBench_Leaderboard"
  ]
 },
 {
  "model": "jt-cv",
  "benchmark": "vbench-2-0",
  "score": 64.6,
  "unit": "%",
  "provenance": "maintainer-run",
  "setting": "Total score",
  "view": "VBench-2.0",
  "rank": 2,
  "rank_population": null,
  "date": "2026-04-01",
  "sources": [
   "https://huggingface.co/spaces/Vchitect/VBench_Leaderboard"
  ]
 },
 {
  "model": "jt3-5",
  "benchmark": "vbench",
  "score": 86.47,
  "unit": "%",
  "provenance": "maintainer-run",
  "setting": "Total score; submission-based board",
  "view": "VBench (v1) text-to-video",
  "rank": 5,
  "rank_population": null,
  "date": "2025-07-30",
  "sources": [
   "https://huggingface.co/spaces/Vchitect/VBench_Leaderboard"
  ]
 },
 {
  "model": "jt3-5",
  "benchmark": "vbench",
  "score": 87.04,
  "unit": "%",
  "provenance": "maintainer-run",
  "setting": "Quality score; submission-based board",
  "view": "VBench (v1) text-to-video",
  "rank": null,
  "rank_population": null,
  "date": "2025-07-30",
  "sources": [
   "https://huggingface.co/spaces/Vchitect/VBench_Leaderboard"
  ]
 },
 {
  "model": "keisler-2022",
  "benchmark": "weatherbench-2",
  "score": 174.7,
  "unit": "RMSE m2/s2",
  "provenance": "maintainer-run",
  "setting": "Z500 day 3, deterministic, Keisler (2022) vs ERA5",
  "view": "year 2020, 240x121 grid",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://researchsites.withgoogle.com/weatherbench/deterministic/"
  ]
 },
 {
  "model": "keisler-2022",
  "benchmark": "weatherbench-2",
  "score": 346,
  "unit": "RMSE m2/s2",
  "provenance": "maintainer-run",
  "setting": "Z500 day 5, deterministic, Keisler (2022) vs ERA5",
  "view": "year 2020, 240x121 grid",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://researchsites.withgoogle.com/weatherbench/deterministic/"
  ]
 },
 {
  "model": "keisler-2022",
  "benchmark": "weatherbench-2",
  "score": 66.9,
  "unit": "RMSE m2/s2",
  "provenance": "maintainer-run",
  "setting": "Z500 day 1, deterministic, Keisler (2022) vs ERA5",
  "view": "year 2020, 240x121 grid",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://researchsites.withgoogle.com/weatherbench/deterministic/"
  ]
 },
 {
  "model": "keisler-2022",
  "benchmark": "weatherbench-2",
  "score": 787,
  "unit": "RMSE m2/s2",
  "provenance": "maintainer-run",
  "setting": "Z500 day 10, deterministic, Keisler (2022) vs ERA5",
  "view": "year 2020, 240x121 grid",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://researchsites.withgoogle.com/weatherbench/deterministic/"
  ]
 },
 {
  "model": "krea-2-large",
  "benchmark": "aa-image-t2i-v2-0",
  "score": 1026,
  "unit": "Elo",
  "provenance": "independent",
  "setting": "rank shown as 22-31",
  "view": "AA Text-to-Image Arena, overall",
  "rank": 22,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://artificialanalysis.ai/text-to-image/arena/leaderboard-text"
  ]
 },
 {
  "model": "kuaishou-kling-1-6",
  "benchmark": "vbench-2-0",
  "score": 48.58,
  "unit": "%",
  "provenance": "maintainer-run",
  "setting": "Creativity score",
  "view": "VBench-2.0",
  "rank": null,
  "rank_population": null,
  "date": "2025-03-28",
  "sources": [
   "https://huggingface.co/spaces/Vchitect/VBench_Leaderboard"
  ]
 },
 {
  "model": "kuaishou-kling-1-6",
  "benchmark": "vbench-2-0",
  "score": 59,
  "unit": "%",
  "provenance": "maintainer-run",
  "setting": "Total score",
  "view": "VBench-2.0",
  "rank": 8,
  "rank_population": null,
  "date": "2025-03-28",
  "sources": [
   "https://huggingface.co/spaces/Vchitect/VBench_Leaderboard"
  ]
 },
 {
  "model": "kuaishou-kling-3-0-omni",
  "benchmark": "aa-video-t2v",
  "score": 1015,
  "unit": "Elo",
  "provenance": "independent",
  "setting": "1080p (Pro)",
  "view": "AA Text-to-Video leaderboard",
  "rank": 15,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://artificialanalysis.ai/video/leaderboard/text-to-video"
  ]
 },
 {
  "model": "kuaishou-kling-3-0",
  "benchmark": "aa-video-t2v",
  "score": 1000,
  "unit": "Elo",
  "provenance": "independent",
  "setting": "1080p (Pro); anchor",
  "view": "AA Text-to-Video leaderboard",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://artificialanalysis.ai/video/leaderboard/text-to-video"
  ]
 },
 {
  "model": "layer-6-ai-tabdpt",
  "benchmark": "tabarena",
  "score": 1460,
  "unit": "Elo",
  "provenance": "maintainer-run",
  "setting": "tuned + ensembled",
  "view": "All Tasks, no imputation, snapshot 2026-05-06, 59 entries",
  "rank": 9,
  "rank_population": 59,
  "date": "2026-05-06",
  "sources": [
   "https://benchmarklist.com/benchmarks/tabarena_all/",
   "https://benchmarklist.com/benchmarks/tabarena_all/"
  ]
 },
 {
  "model": "lg-ai-research-exaone-4-0-32b",
  "benchmark": "aime-2025",
  "score": 85.3,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "Reasoning mode",
  "view": "EXAONE 4.0 model card",
  "rank": null,
  "rank_population": null,
  "date": "2025-07",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://huggingface.co/LGAI-EXAONE/EXAONE-4.0-32B"
  ]
 },
 {
  "model": "lg-ai-research-exaone-4-0-32b",
  "benchmark": "gpqa-diamond",
  "score": 75.4,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "Reasoning mode",
  "view": "EXAONE 4.0 model card",
  "rank": null,
  "rank_population": null,
  "date": "2025-07",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://huggingface.co/LGAI-EXAONE/EXAONE-4.0-32B"
  ]
 },
 {
  "model": "lg-ai-research-exaone-4-0-32b",
  "benchmark": "livecodebench-v6",
  "score": 66.7,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "Reasoning mode",
  "view": "EXAONE 4.0 model card",
  "rank": null,
  "rank_population": null,
  "date": "2025-07",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://huggingface.co/LGAI-EXAONE/EXAONE-4.0-32B"
  ]
 },
 {
  "model": "lg-ai-research-exaone-4-0-32b",
  "benchmark": "mmlu-pro",
  "score": 81.8,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "Reasoning mode",
  "view": "EXAONE 4.0 model card",
  "rank": null,
  "rank_population": null,
  "date": "2025-07",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://huggingface.co/LGAI-EXAONE/EXAONE-4.0-32B"
  ]
 },
 {
  "model": "lg-ai-research-exaone-forecast",
  "benchmark": "gift-eval",
  "score": 0.46,
  "unit": "CRPS (geo-mean, normalised to Seasonal Naive)",
  "provenance": "independent",
  "setting": "zero-shot; rank is average CRPS rank",
  "view": "Leaderboard rebuilt from the published raw results, 143 entries covering all 97 configurations",
  "rank": 22,
  "rank_population": 143,
  "date": "2026-10-09",
  "sources": [
   "https://huggingface.co/spaces/Salesforce/GIFT-Eval"
  ],
  "leakage": "no",
  "leakage_note": "Test Leak. column: No (EXAONE-Forecast)"
 },
 {
  "model": "lg-ai-research-exaone-forecast",
  "benchmark": "gift-eval",
  "score": 0.673,
  "unit": "MASE (geo-mean, normalised to Seasonal Naive)",
  "provenance": "independent",
  "setting": "zero-shot",
  "view": "Leaderboard rebuilt from the published raw results, 143 entries covering all 97 configurations",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-09",
  "sources": [
   "https://huggingface.co/spaces/Salesforce/GIFT-Eval"
  ],
  "leakage": "no",
  "leakage_note": "Test Leak. column: No (EXAONE-Forecast)"
 },
 {
  "model": "lg-ai-research-k-exaone-2-0",
  "benchmark": "aa-intelligence-index",
  "score": 20,
  "unit": "index",
  "provenance": "independent",
  "setting": "asterisk on page",
  "view": "AA leaderboard, 205 current models",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://artificialanalysis.ai/leaderboards/models"
  ]
 },
 {
  "model": "lg-ai-research-k-exaone-2-0",
  "benchmark": "gpqa-diamond",
  "score": 82.2,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/LGAI-EXAONE/K-EXAONE-2.0-750B-A37B"
  ]
 },
 {
  "model": "lg-ai-research-k-exaone-2-0",
  "benchmark": "kgc-safety",
  "score": 99.8,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/LGAI-EXAONE/K-EXAONE-2.0-750B-A37B"
  ]
 },
 {
  "model": "lg-ai-research-k-exaone-2-0",
  "benchmark": "mmlu-pro",
  "score": 83.5,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/LGAI-EXAONE/K-EXAONE-2.0-750B-A37B"
  ]
 },
 {
  "model": "lg-ai-research-k-exaone-2-0",
  "benchmark": "swe-bench-verified",
  "score": 68.2,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/LGAI-EXAONE/K-EXAONE-2.0-750B-A37B"
  ]
 },
 {
  "model": "lightricks-ltx-2-5-fast",
  "benchmark": "aa-video-t2v",
  "score": 946,
  "unit": "Elo",
  "provenance": "independent",
  "setting": null,
  "view": "AA Text-to-Video leaderboard",
  "rank": 23,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://artificialanalysis.ai/video/leaderboard/text-to-video"
  ]
 },
 {
  "model": "lightricks-ltx-2-5-pro",
  "benchmark": "aa-video-t2v",
  "score": 943,
  "unit": "Elo",
  "provenance": "independent",
  "setting": null,
  "view": "AA Text-to-Video leaderboard",
  "rank": 24,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://artificialanalysis.ai/video/leaderboard/text-to-video"
  ]
 },
 {
  "model": "limo",
  "benchmark": "aime-2024",
  "score": 63.3,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2025-02",
  "sources": [
   "https://arxiv.org/abs/2502.03387"
  ]
 },
 {
  "model": "limo",
  "benchmark": "math-500",
  "score": 95.6,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2025-02",
  "sources": [
   "https://arxiv.org/abs/2502.03387"
  ]
 },
 {
  "model": "lingzhi-72b-chat",
  "benchmark": "cmmlu",
  "score": 90.26,
  "unit": "%",
  "provenance": "maintainer-run",
  "setting": "Five-shot",
  "view": "CMMLU leaderboard",
  "rank": 1,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://github.com/haonan-li/CMMLU"
  ],
  "unverified": []
 },
 {
  "model": "liquid-ai-lfm2-5-8b-a1b",
  "benchmark": "ifeval",
  "score": 91.84,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/LiquidAI/LFM2.5-8B-A1B"
  ]
 },
 {
  "model": "liquid-ai-lfm2-5-8b-a1b",
  "benchmark": "math-500",
  "score": 88.76,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/LiquidAI/LFM2.5-8B-A1B"
  ]
 },
 {
  "model": "luciddreamer",
  "benchmark": "worldscore",
  "score": 49.28,
  "unit": "score",
  "provenance": "maintainer-run",
  "setting": "Dynamic aggregate",
  "view": "WorldScore paper table",
  "rank": null,
  "rank_population": null,
  "date": "2025",
  "sources": [
   "https://arxiv.org/html/2504.00983v2"
  ]
 },
 {
  "model": "luciddreamer",
  "benchmark": "worldscore",
  "score": 70.4,
  "unit": "score",
  "provenance": "maintainer-run",
  "setting": "Static aggregate",
  "view": "WorldScore paper table",
  "rank": null,
  "rank_population": null,
  "date": "2025",
  "sources": [
   "https://arxiv.org/html/2504.00983v2"
  ]
 },
 {
  "model": "luma-ai-photon",
  "benchmark": "aa-image-t2i-v2-0",
  "score": 885,
  "unit": "Elo",
  "provenance": "independent",
  "setting": "Rank range 105 to 116",
  "view": "AA Text-to-Image Arena, 168 models",
  "rank": 111,
  "rank_population": 168,
  "date": "2026-10-11",
  "uncertainty": "878 to 892 (+/-7)",
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://artificialanalysis.ai/image/leaderboard/text-to-image"
  ]
 },
 {
  "model": "luma-ai-uni-1-1-max",
  "benchmark": "lmarena-text-to-image",
  "score": 1189,
  "unit": "Elo",
  "provenance": "independent",
  "setting": null,
  "view": "LMArena Text-to-Image, overall, updated 7 Oct 2026",
  "rank": 22,
  "rank_population": null,
  "date": "2026-10-07",
  "sources": [
   "https://arena.ai/leaderboard/text-to-image"
  ],
  "uncertainty": "±6"
 },
 {
  "model": "luma-ai-uni-1-1",
  "benchmark": "lmarena-text-to-image",
  "score": 1184,
  "unit": "Elo",
  "provenance": "independent",
  "setting": null,
  "view": "LMArena Text-to-Image, overall, updated 7 Oct 2026",
  "rank": 23,
  "rank_population": null,
  "date": "2026-10-07",
  "sources": [
   "https://arena.ai/leaderboard/text-to-image"
  ],
  "uncertainty": "±4"
 },
 {
  "model": "lumina-dimoo-w-self-grpo",
  "benchmark": "geneval",
  "score": 0.91,
  "unit": "score",
  "provenance": "vendor-reported",
  "setting": "paper-reported, labelled unverified by Codesota; year 2025",
  "view": "Codesota aggregator",
  "rank": 1,
  "rank_population": 7,
  "date": "2025-10-07",
  "sources": [
   "https://arxiv.org/abs/2510.06308",
   "https://www.codesota.com/benchmark/geneval"
  ]
 },
 {
  "model": "m42-med42-llama3-70b",
  "benchmark": "medmcqa",
  "score": 73.2,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2024-08",
  "sources": [
   "https://huggingface.co/m42-health/Llama3-Med42-70B"
  ]
 },
 {
  "model": "m42-med42-llama3-70b",
  "benchmark": "medqa",
  "score": 79.1,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2024-08",
  "sources": [
   "https://huggingface.co/m42-health/Llama3-Med42-70B"
  ]
 },
 {
  "model": "m42-med42-llama3-70b",
  "benchmark": "usmle",
  "score": 83.8,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2024-08",
  "sources": [
   "https://huggingface.co/m42-health/Llama3-Med42-70B"
  ]
 },
 {
  "model": "m42-med42-llama3-8b",
  "benchmark": "medqa",
  "score": 62.84,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2024-08",
  "sources": [
   "https://huggingface.co/m42-health/Llama3-Med42-70B"
  ]
 },
 {
  "model": "mahmood-lab-uni",
  "benchmark": "virchow-pan-cancer-detection",
  "score": 0.94,
  "unit": "AUROC",
  "provenance": "vendor-reported",
  "setting": "As reported in the Virchow paper",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2024-07-22",
  "sources": [
   "https://www.nature.com/articles/s41591-024-03141-0"
  ]
 },
 {
  "model": "matris-10m-oam",
  "benchmark": "matbench-discovery",
  "score": 0.218,
  "unit": "kSRME",
  "provenance": "maintainer-run",
  "setting": "lower is better",
  "view": "leaderboard fetched 2026-10-10",
  "rank": null,
  "rank_population": null,
  "date": "2025-10-29",
  "sources": [
   "https://matbench-discovery.materialsproject.org/"
  ]
 },
 {
  "model": "matris-10m-oam",
  "benchmark": "matbench-discovery",
  "score": 0.877,
  "unit": "CPS",
  "provenance": "maintainer-run",
  "setting": null,
  "view": "leaderboard fetched 2026-10-10, ranked by CPS",
  "rank": 5,
  "rank_population": null,
  "date": "2025-10-29",
  "sources": [
   "https://matbench-discovery.materialsproject.org/"
  ]
 },
 {
  "model": "matris-10m-oam",
  "benchmark": "matbench-discovery",
  "score": 0.921,
  "unit": "F1",
  "provenance": "maintainer-run",
  "setting": null,
  "view": "leaderboard fetched 2026-10-10",
  "rank": null,
  "rank_population": null,
  "date": "2025-10-29",
  "sources": [
   "https://matbench-discovery.materialsproject.org/"
  ]
 },
 {
  "model": "meituan-longcat-flash",
  "benchmark": "gpqa-diamond",
  "score": 73.23,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "acc",
  "view": "LongCat-Flash-Chat model card",
  "rank": null,
  "rank_population": null,
  "date": "2025-09",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://huggingface.co/meituan-longcat/LongCat-Flash-Chat"
  ]
 },
 {
  "model": "meituan-longcat-flash",
  "benchmark": "mmlu-pro",
  "score": 82.68,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "acc",
  "view": "LongCat-Flash-Chat model card",
  "rank": null,
  "rank_population": null,
  "date": "2025-09",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://huggingface.co/meituan-longcat/LongCat-Flash-Chat"
  ]
 },
 {
  "model": "meituan-longcat-flash",
  "benchmark": "mmlu",
  "score": 89.71,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "acc",
  "view": "LongCat-Flash-Chat model card",
  "rank": null,
  "rank_population": null,
  "date": "2025-09",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://huggingface.co/meituan-longcat/LongCat-Flash-Chat"
  ]
 },
 {
  "model": "meituan-longcat-flash",
  "benchmark": "swe-bench-verified",
  "score": 60.4,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "acc",
  "view": "LongCat-Flash-Chat model card",
  "rank": null,
  "rank_population": null,
  "date": "2025-09",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://huggingface.co/meituan-longcat/LongCat-Flash-Chat"
  ]
 },
 {
  "model": "meituan-longcat-flash",
  "benchmark": "tau2-bench",
  "score": 73.68,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "Telecom, avg@4",
  "view": "LongCat-Flash-Chat model card",
  "rank": null,
  "rank_population": null,
  "date": "2025-09",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://huggingface.co/meituan-longcat/LongCat-Flash-Chat"
  ]
 },
 {
  "model": "meta-esen-30m-oam",
  "benchmark": "matbench-discovery",
  "score": 0.17,
  "unit": "kSRME",
  "provenance": "maintainer-run",
  "setting": "lower is better",
  "view": "leaderboard fetched 2026-10-10",
  "rank": null,
  "rank_population": null,
  "date": "2025-03-17",
  "sources": [
   "https://matbench-discovery.materialsproject.org/"
  ]
 },
 {
  "model": "meta-esen-30m-oam",
  "benchmark": "matbench-discovery",
  "score": 0.888,
  "unit": "CPS",
  "provenance": "maintainer-run",
  "setting": null,
  "view": "leaderboard fetched 2026-10-10, ranked by CPS",
  "rank": 2,
  "rank_population": null,
  "date": "2025-03-17",
  "sources": [
   "https://matbench-discovery.materialsproject.org/"
  ]
 },
 {
  "model": "meta-esen-30m-oam",
  "benchmark": "matbench-discovery",
  "score": 0.925,
  "unit": "F1",
  "provenance": "maintainer-run",
  "setting": null,
  "view": "leaderboard fetched 2026-10-10",
  "rank": null,
  "rank_population": null,
  "date": "2025-03-17",
  "sources": [
   "https://matbench-discovery.materialsproject.org/"
  ]
 },
 {
  "model": "meta-llama-3-1-8b-instruct",
  "benchmark": "sea-helm",
  "score": 37.2,
  "unit": "score",
  "provenance": "maintainer-run",
  "setting": "Checkpoint Llama-3.1-8B-Instruct as listed; release view (data last updated 18 Sep 2026); score is the average of 2000 bootstraps",
  "view": "SEA-HELM leaderboard, 58 models, SEA average",
  "rank": null,
  "rank_population": null,
  "date": "2026-09-18",
  "uncertainty": "95% CI [-0.65, +0.67]",
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://leaderboard.sea-lion.ai/detailed/SEA"
  ]
 },
 {
  "model": "meta-llama-3-1-8b-instruct",
  "benchmark": "sea-helm",
  "score": 54.48,
  "unit": "score",
  "provenance": "maintainer-run",
  "setting": "Checkpoint Llama-3.1-8B-Instruct as listed; release view (data last updated 18 Sep 2026); score is the average of 2000 bootstraps",
  "view": "SEA-HELM leaderboard, 58 models, Indonesian (ID)",
  "rank": null,
  "rank_population": null,
  "date": "2026-09-18",
  "uncertainty": "95% CI [-1.57, +1.56]",
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://leaderboard.sea-lion.ai/detailed/ID"
  ]
 },
 {
  "model": "meta-llama-3-3-70b-instruct",
  "benchmark": "sea-helm",
  "score": 60.44,
  "unit": "score",
  "provenance": "maintainer-run",
  "setting": "Checkpoint Llama-3.3-70B-Instruct as listed; release view (data last updated 18 Sep 2026); score is the average of 2000 bootstraps",
  "view": "SEA-HELM leaderboard, 58 models, SEA average",
  "rank": null,
  "rank_population": null,
  "date": "2026-09-18",
  "uncertainty": "95% CI [-0.70, +0.70]",
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://leaderboard.sea-lion.ai/detailed/SEA"
  ]
 },
 {
  "model": "meta-llama-3-3-70b-instruct",
  "benchmark": "sea-helm",
  "score": 71.37,
  "unit": "score",
  "provenance": "maintainer-run",
  "setting": "Checkpoint Llama-3.3-70B-Instruct as listed; release view (data last updated 18 Sep 2026); score is the average of 2000 bootstraps",
  "view": "SEA-HELM leaderboard, 58 models, Indonesian (ID)",
  "rank": null,
  "rank_population": null,
  "date": "2026-09-18",
  "uncertainty": "95% CI [-1.50, +1.54]",
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://leaderboard.sea-lion.ai/detailed/ID"
  ]
 },
 {
  "model": "meta-llama-4-scout",
  "benchmark": "sea-helm",
  "score": 63.43,
  "unit": "score",
  "provenance": "maintainer-run",
  "setting": "Checkpoint Llama-4-Scout-17B-16E-Instruct as listed; release view (data last updated 18 Sep 2026); score is the average of 2000 bootstraps",
  "view": "SEA-HELM leaderboard, 58 models, SEA average",
  "rank": null,
  "rank_population": null,
  "date": "2026-09-18",
  "uncertainty": "95% CI [-0.78, +0.79]",
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://leaderboard.sea-lion.ai/detailed/SEA"
  ]
 },
 {
  "model": "meta-llama-4-scout",
  "benchmark": "sea-helm",
  "score": 67.86,
  "unit": "score",
  "provenance": "maintainer-run",
  "setting": "Checkpoint Llama-4-Scout-17B-16E-Instruct as listed; release view (data last updated 18 Sep 2026); score is the average of 2000 bootstraps",
  "view": "SEA-HELM leaderboard, 58 models, Indonesian (ID)",
  "rank": null,
  "rank_population": null,
  "date": "2026-09-18",
  "uncertainty": "95% CI [-1.58, +1.56]",
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://leaderboard.sea-lion.ai/detailed/ID"
  ]
 },
 {
  "model": "meta-mms-1b-all",
  "benchmark": "idsv",
  "score": 29.3,
  "unit": "WER",
  "provenance": "independent",
  "setting": "IDSV test, all, zero-shot",
  "view": "Table 3",
  "rank": null,
  "rank_population": null,
  "date": "2024-10",
  "sources": [
   "https://arxiv.org/html/2410.08828v2"
  ]
 },
 {
  "model": "meta-mms-1b-all",
  "benchmark": "idsv",
  "score": 9.57,
  "unit": "CER",
  "provenance": "independent",
  "setting": "IDSV test, all, zero-shot",
  "view": "Table 3",
  "rank": null,
  "rank_population": null,
  "date": "2024-10",
  "sources": [
   "https://arxiv.org/html/2410.08828v2"
  ]
 },
 {
  "model": "meta-muse-glimmer-30b",
  "benchmark": "mcp-atlas",
  "score": 75.5,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/meta-models/Muse-Glimmer-30B"
  ]
 },
 {
  "model": "meta-muse-glimmer-30b",
  "benchmark": "sea-helm",
  "score": 72.13,
  "unit": "score",
  "provenance": "maintainer-run",
  "setting": null,
  "view": "SEA-HELM SEA average, open-weight models",
  "rank": null,
  "rank_population": null,
  "date": "2026-09-18",
  "sources": [
   "https://leaderboard.sea-lion.ai/detailed/SEA"
  ],
  "uncertainty": "95% CI [-0.59, +0.56]"
 },
 {
  "model": "meta-muse-glimmer-30b",
  "benchmark": "sea-helm",
  "score": 75.61,
  "unit": "score",
  "provenance": "maintainer-run",
  "setting": null,
  "view": "SEA-HELM Indonesian, open-weight models, average of 2,000 bootstraps",
  "rank": 5,
  "rank_population": null,
  "date": "2026-09-18",
  "sources": [
   "https://leaderboard.sea-lion.ai/detailed/ID"
  ],
  "uncertainty": "95% CI [-1.13, +1.10]"
 },
 {
  "model": "meta-muse-glimmer-30b",
  "benchmark": "swe-bench-verified",
  "score": 76,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/meta-models/Muse-Glimmer-30B"
  ]
 },
 {
  "model": "meta-muse-image",
  "benchmark": "aa-image-t2i-v2-0",
  "score": 1116,
  "unit": "Elo",
  "provenance": "independent",
  "setting": "rank shown as 8-10",
  "view": "AA Text-to-Image Arena, overall",
  "rank": 8,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://artificialanalysis.ai/text-to-image/arena/leaderboard-text"
  ]
 },
 {
  "model": "meta-muse-image",
  "benchmark": "lmarena-text-to-image",
  "score": 1274,
  "unit": "Elo",
  "provenance": "independent",
  "setting": null,
  "view": "LMArena Text-to-Image, overall, updated 7 Oct 2026",
  "rank": 9,
  "rank_population": null,
  "date": "2026-10-07",
  "sources": [
   "https://arena.ai/leaderboard/text-to-image"
  ],
  "uncertainty": "±5"
 },
 {
  "model": "meta-muse-spark-1-1",
  "benchmark": "lmarena-vision",
  "score": 1280,
  "unit": "Elo",
  "provenance": "independent",
  "setting": null,
  "view": "Arena Vision overall, style control default, 165 models",
  "rank": 28,
  "rank_population": 165,
  "date": "2026-10-09",
  "sources": [
   "https://arena.ai/leaderboard/chat/vision"
  ],
  "uncertainty": "±7"
 },
 {
  "model": "meta-muse-spark-1-1",
  "benchmark": "swe-bench-pro",
  "score": 61.5,
  "unit": "%",
  "provenance": "maintainer-run",
  "setting": "Scale SEAL public, mini-swe-agent, +/-3.10",
  "view": "Scale SEAL SWE-Bench Pro public",
  "rank": 1,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://labs.scale.com/leaderboard/swe_bench_pro_public"
  ],
  "uncertainty": "±3.10"
 },
 {
  "model": "meta-muse-spark-1-2",
  "benchmark": "lmarena-vision",
  "score": 1293,
  "unit": "Elo",
  "provenance": "independent",
  "setting": "xHigh",
  "view": "Arena Vision overall, style control default, 165 models",
  "rank": 10,
  "rank_population": 165,
  "date": "2026-10-09",
  "sources": [
   "https://arena.ai/leaderboard/chat/vision"
  ],
  "uncertainty": "±14"
 },
 {
  "model": "meta-muse-spark-1-3",
  "benchmark": "aa-intelligence-index",
  "score": 48,
  "unit": "index",
  "provenance": "independent",
  "setting": "max",
  "view": "AA leaderboard, 205 current models",
  "rank": 19,
  "rank_population": 205,
  "date": "2026-10-10",
  "sources": [
   "https://artificialanalysis.ai/leaderboards/models"
  ]
 },
 {
  "model": "meta-muse-spark-1-3",
  "benchmark": "aa-intelligence-index",
  "score": 48,
  "unit": "index",
  "provenance": "independent",
  "setting": "max",
  "view": "AA model page, 227 models",
  "rank": 23,
  "rank_population": 227,
  "date": "2026-10-10",
  "sources": [
   "https://artificialanalysis.ai/models/muse-spark-1-3"
  ]
 },
 {
  "model": "meta-muse-spark-1-3",
  "benchmark": "lmarena-text",
  "score": 1494,
  "unit": "Elo",
  "provenance": "independent",
  "setting": "max",
  "view": "Arena Text overall",
  "rank": 9,
  "rank_population": null,
  "date": "2026-10-08",
  "sources": [
   "https://arena.ai/leaderboard/chat/text"
  ],
  "uncertainty": "±6"
 },
 {
  "model": "meta-muse-spark-1-3",
  "benchmark": "lmarena-vision",
  "score": 1286,
  "unit": "Elo",
  "provenance": "independent",
  "setting": "xHigh",
  "view": "Arena Vision overall, style control default, 165 models",
  "rank": 18,
  "rank_population": 165,
  "date": "2026-10-09",
  "sources": [
   "https://arena.ai/leaderboard/chat/vision"
  ],
  "uncertainty": "±10"
 },
 {
  "model": "meta-muse-spark-1-3",
  "benchmark": "lmarena-vision",
  "score": 1290,
  "unit": "Elo",
  "provenance": "independent",
  "setting": "max (muse-spark-1.3-max)",
  "view": "Arena Vision overall, style control default, 165 models",
  "rank": 12,
  "rank_population": 165,
  "date": "2026-10-09",
  "sources": [
   "https://arena.ai/leaderboard/chat/vision"
  ],
  "uncertainty": "±10"
 },
 {
  "model": "meta-muse-spark",
  "benchmark": "lmarena-vision",
  "score": 1294,
  "unit": "Elo",
  "provenance": "independent",
  "setting": "muse-spark",
  "view": "Arena Vision overall, style control default, 165 models",
  "rank": 9,
  "rank_population": 165,
  "date": "2026-10-09",
  "sources": [
   "https://arena.ai/leaderboard/chat/vision"
  ],
  "uncertainty": "±9"
 },
 {
  "model": "meta-muse-video",
  "benchmark": "lmarena-text-to-video",
  "score": 1456,
  "unit": "Elo",
  "provenance": "independent",
  "setting": null,
  "view": "LMArena Text-to-Video, updated 21 Sep 2026",
  "rank": 9,
  "rank_population": null,
  "date": "2026-09-21",
  "sources": [
   "https://arena.ai/leaderboard/text-to-video"
  ],
  "uncertainty": "±15"
 },
 {
  "model": "meta-musicgen",
  "benchmark": "aa-music-arena-v1-1",
  "score": 881,
  "unit": "Elo",
  "provenance": "independent",
  "setting": "secondary capture of AA post; lowest reported",
  "view": "AA Music Arena v1.1, board not stated",
  "rank": null,
  "rank_population": null,
  "date": "2026-10",
  "sources": [
   "https://alphasignal.ai/news/artificial-analysis-music-arena-v1-1-crowns-suno-v6-across-1-000-harder-prompts",
   "https://digg.com/ai/g8egglmo"
  ]
 },
 {
  "model": "meta-omnilingual-asr",
  "benchmark": "common-voice-22",
  "score": 6.4,
  "unit": "CER",
  "provenance": "vendor-reported",
  "setting": "7B LLM-ASR, CV22-76, approximate",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2025-11",
  "sources": [
   "https://arxiv.org/pdf/2511.09690"
  ]
 },
 {
  "model": "meta-omnilingual-asr",
  "benchmark": "fleurs",
  "score": 6.2,
  "unit": "CER",
  "provenance": "vendor-reported",
  "setting": "7B LLM-ASR, FLEURS-102, approximate",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2025-11",
  "sources": [
   "https://arxiv.org/pdf/2511.09690"
  ]
 },
 {
  "model": "meta-sam-3",
  "benchmark": "lvis",
  "score": 37.2,
  "unit": "cgF1",
  "provenance": "vendor-reported",
  "setting": "instance segmentation",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2025-11",
  "sources": [
   "https://github.com/facebookresearch/sam3"
  ]
 },
 {
  "model": "meta-sam-3",
  "benchmark": "lvis",
  "score": 40.6,
  "unit": "cgF1",
  "provenance": "vendor-reported",
  "setting": "box",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2025-11",
  "sources": [
   "https://github.com/facebookresearch/sam3"
  ]
 },
 {
  "model": "meta-sam-3",
  "benchmark": "lvis",
  "score": 48.5,
  "unit": "AP",
  "provenance": "vendor-reported",
  "setting": "instance segmentation",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2025-11",
  "sources": [
   "https://github.com/facebookresearch/sam3"
  ]
 },
 {
  "model": "meta-sam-3",
  "benchmark": "sa-co-gold",
  "score": 54.1,
  "unit": "cgF1",
  "provenance": "vendor-reported",
  "setting": "human 72.8",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2025-11",
  "sources": [
   "https://github.com/facebookresearch/sam3"
  ]
 },
 {
  "model": "meta-sam-3",
  "benchmark": "sa-v",
  "score": 30.3,
  "unit": "cgF1",
  "provenance": "vendor-reported",
  "setting": "test; human 53.1",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2025-11",
  "sources": [
   "https://github.com/facebookresearch/sam3"
  ]
 },
 {
  "model": "meta-v-jepa-2",
  "benchmark": "epic-kitchens-100",
  "score": 39.7,
  "unit": "R@5",
  "provenance": "vendor-reported",
  "setting": "anticipation",
  "view": "V-JEPA 2 paper",
  "rank": null,
  "rank_population": null,
  "date": "2025-06",
  "sources": [
   "https://arxiv.org/abs/2506.09985"
  ]
 },
 {
  "model": "meta-v-jepa-2",
  "benchmark": "perceptiontest",
  "score": 84,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "8B LLM-aligned scale",
  "view": "V-JEPA 2 paper",
  "rank": null,
  "rank_population": null,
  "date": "2025-06",
  "sources": [
   "https://arxiv.org/abs/2506.09985"
  ]
 },
 {
  "model": "meta-v-jepa-2",
  "benchmark": "ssv2",
  "score": 77.3,
  "unit": "% top-1",
  "provenance": "vendor-reported",
  "setting": null,
  "view": "V-JEPA 2 paper",
  "rank": null,
  "rank_population": null,
  "date": "2025-06",
  "sources": [
   "https://arxiv.org/abs/2506.09985"
  ]
 },
 {
  "model": "meta-v-jepa-2",
  "benchmark": "tempcompass",
  "score": 76.9,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "8B LLM-aligned scale",
  "view": "V-JEPA 2 paper",
  "rank": null,
  "rank_population": null,
  "date": "2025-06",
  "sources": [
   "https://arxiv.org/abs/2506.09985"
  ]
 },
 {
  "model": "microsoft-ai-mai-image-2-6",
  "benchmark": "aa-image-t2i-v2-0",
  "score": 1151,
  "unit": "Elo",
  "provenance": "independent",
  "setting": "rank shown as 5-6",
  "view": "AA Text-to-Image Arena, overall",
  "rank": 5,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://artificialanalysis.ai/text-to-image/arena/leaderboard-text"
  ]
 },
 {
  "model": "microsoft-ai-mai-image-2-6",
  "benchmark": "lmarena-text-to-image",
  "score": 1332,
  "unit": "Elo",
  "provenance": "independent",
  "setting": null,
  "view": "LMArena Text-to-Image, overall, updated 7 Oct 2026",
  "rank": 5,
  "rank_population": null,
  "date": "2026-10-07",
  "sources": [
   "https://arena.ai/leaderboard/text-to-image"
  ],
  "uncertainty": "±5"
 },
 {
  "model": "microsoft-aurora",
  "benchmark": "weatherbench-2",
  "score": 1.501,
  "unit": "RMSE K",
  "provenance": "maintainer-run",
  "setting": "T850 day 5, deterministic, Aurora (oper.) vs Analysis",
  "view": "year 2022, 240x121 grid",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://researchsites.withgoogle.com/weatherbench/deterministic/"
  ]
 },
 {
  "model": "microsoft-aurora",
  "benchmark": "weatherbench-2",
  "score": 119.8,
  "unit": "RMSE m2/s2",
  "provenance": "maintainer-run",
  "setting": "Z500 day 3, deterministic, Aurora (oper.) vs Analysis",
  "view": "year 2022, 240x121 grid",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://researchsites.withgoogle.com/weatherbench/deterministic/"
  ]
 },
 {
  "model": "microsoft-aurora",
  "benchmark": "weatherbench-2",
  "score": 2.979,
  "unit": "RMSE K",
  "provenance": "maintainer-run",
  "setting": "T850 day 10, deterministic, Aurora (oper.) vs Analysis",
  "view": "year 2022, 240x121 grid",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://researchsites.withgoogle.com/weatherbench/deterministic/"
  ]
 },
 {
  "model": "microsoft-aurora",
  "benchmark": "weatherbench-2",
  "score": 262.8,
  "unit": "RMSE m2/s2",
  "provenance": "maintainer-run",
  "setting": "Z500 day 5, deterministic, Aurora (oper.) vs Analysis",
  "view": "year 2022, 240x121 grid",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://researchsites.withgoogle.com/weatherbench/deterministic/"
  ]
 },
 {
  "model": "microsoft-aurora",
  "benchmark": "weatherbench-2",
  "score": 38.1,
  "unit": "RMSE m2/s2",
  "provenance": "maintainer-run",
  "setting": "Z500 day 1, deterministic, Aurora (oper.) vs Analysis",
  "view": "year 2022, 240x121 grid",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://researchsites.withgoogle.com/weatherbench/deterministic/"
  ]
 },
 {
  "model": "microsoft-aurora",
  "benchmark": "weatherbench-2",
  "score": 668.4,
  "unit": "RMSE m2/s2",
  "provenance": "maintainer-run",
  "setting": "Z500 day 10, deterministic, Aurora (oper.) vs Analysis",
  "view": "year 2022, 240x121 grid",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://researchsites.withgoogle.com/weatherbench/deterministic/"
  ]
 },
 {
  "model": "microsoft-lightgbm",
  "benchmark": "tabarena",
  "score": 1188,
  "unit": "Elo",
  "provenance": "maintainer-run",
  "setting": "default",
  "view": "All Tasks, no imputation, snapshot 2026-05-06, 59 entries",
  "rank": 38,
  "rank_population": 59,
  "date": "2026-05-06",
  "sources": [
   "https://benchmarklist.com/benchmarks/tabarena_all/"
  ]
 },
 {
  "model": "microsoft-lightgbm",
  "benchmark": "tabarena",
  "score": 1387,
  "unit": "Elo",
  "provenance": "maintainer-run",
  "setting": "tuned",
  "view": "All Tasks, no imputation, snapshot 2026-05-06, 59 entries",
  "rank": 18,
  "rank_population": 59,
  "date": "2026-05-06",
  "sources": [
   "https://benchmarklist.com/benchmarks/tabarena_all/"
  ]
 },
 {
  "model": "microsoft-lightgbm",
  "benchmark": "tabarena",
  "score": 1435,
  "unit": "Elo",
  "provenance": "maintainer-run",
  "setting": "tuned + ensembled",
  "view": "All Tasks, no imputation, snapshot 2026-05-06, 59 entries",
  "rank": 11,
  "rank_population": 59,
  "date": "2026-05-06",
  "sources": [
   "https://benchmarklist.com/benchmarks/tabarena_all/"
  ]
 },
 {
  "model": "microsoft-phi-3-mini",
  "benchmark": "mmlu",
  "score": 69,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2024-04",
  "sources": [
   "https://arxiv.org/abs/2404.14219"
  ]
 },
 {
  "model": "microsoft-phi-4-mini-flash-reasoning",
  "benchmark": "aime-2024",
  "score": 52.29,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/microsoft/Phi-4-mini-flash-reasoning"
  ],
  "unverified": []
 },
 {
  "model": "microsoft-phi-4-mini-flash-reasoning",
  "benchmark": "aime-2025",
  "score": 33.59,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/microsoft/Phi-4-mini-flash-reasoning"
  ],
  "unverified": []
 },
 {
  "model": "microsoft-phi-4-mini-flash-reasoning",
  "benchmark": "gpqa-diamond",
  "score": 45.08,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/microsoft/Phi-4-mini-flash-reasoning"
  ],
  "unverified": []
 },
 {
  "model": "microsoft-phi-4-mini-flash-reasoning",
  "benchmark": "math-500",
  "score": 92.45,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/microsoft/Phi-4-mini-flash-reasoning"
  ],
  "unverified": []
 },
 {
  "model": "microsoft-phi-4-mini-instruct",
  "benchmark": "gpqa",
  "score": 25.2,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "0-shot CoT",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/microsoft/Phi-4-mini-instruct"
  ],
  "unverified": []
 },
 {
  "model": "microsoft-phi-4-mini-instruct",
  "benchmark": "gsm8k",
  "score": 88.6,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/microsoft/Phi-4-mini-instruct"
  ],
  "unverified": []
 },
 {
  "model": "microsoft-phi-4-mini-instruct",
  "benchmark": "math",
  "score": 64,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/microsoft/Phi-4-mini-instruct"
  ],
  "unverified": []
 },
 {
  "model": "microsoft-phi-4-mini-instruct",
  "benchmark": "mmlu-pro",
  "score": 52.8,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/microsoft/Phi-4-mini-instruct"
  ],
  "unverified": []
 },
 {
  "model": "microsoft-phi-4-mini-instruct",
  "benchmark": "mmlu",
  "score": 67.3,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "5-shot",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/microsoft/Phi-4-mini-instruct"
  ],
  "unverified": []
 },
 {
  "model": "microsoft-phi-4-mini-instruct",
  "benchmark": "multilingual-mmlu",
  "score": 49.3,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/microsoft/Phi-4-mini-instruct"
  ],
  "unverified": []
 },
 {
  "model": "microsoft-phi-4-multimodal-instruct",
  "benchmark": "open-asr-leaderboard",
  "score": 6.02,
  "unit": "WER",
  "provenance": "maintainer-run",
  "setting": "eight-set macro-average English WER",
  "view": "snapshot 2026-05-06 via benchmarklist",
  "rank": null,
  "rank_population": null,
  "date": "2026-05-06",
  "sources": [
   "https://benchmarklist.com/benchmarks/open_asr_leaderboard/"
  ]
 },
 {
  "model": "microsoft-phi-4-reasoning-vision-15b",
  "benchmark": "ai2d",
  "score": 84.8,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/microsoft/Phi-4-reasoning-vision-15B"
  ]
 },
 {
  "model": "microsoft-phi-4-reasoning-vision-15b",
  "benchmark": "mmmu",
  "score": 54.3,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/microsoft/Phi-4-reasoning-vision-15B"
  ]
 },
 {
  "model": "minimax-h3-max",
  "benchmark": "aa-video-t2v",
  "score": 1130,
  "unit": "Elo",
  "provenance": "independent",
  "setting": null,
  "view": "AA Text-to-Video leaderboard",
  "rank": 5,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://artificialanalysis.ai/video/leaderboard/text-to-video"
  ]
 },
 {
  "model": "minimax-h3",
  "benchmark": "aa-video-t2v",
  "score": 1137,
  "unit": "Elo",
  "provenance": "independent",
  "setting": "768p; top open-weights",
  "view": "AA Text-to-Video leaderboard",
  "rank": 4,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://artificialanalysis.ai/video/leaderboard/text-to-video"
  ]
 },
 {
  "model": "minimax-h3",
  "benchmark": "lmarena-text-to-video",
  "score": 1460,
  "unit": "Elo",
  "provenance": "independent",
  "setting": null,
  "view": "LMArena Text-to-Video, updated 21 Sep 2026",
  "rank": 8,
  "rank_population": null,
  "date": "2026-09-21",
  "sources": [
   "https://arena.ai/leaderboard/text-to-video"
  ],
  "uncertainty": "±9"
 },
 {
  "model": "minimax-minimax-m2-5",
  "benchmark": "swe-bench-verified",
  "score": 80.2,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://leaderboard.steel.dev/leaderboards/swe-bench-verified.md"
  ]
 },
 {
  "model": "minimax-minimax-m3",
  "benchmark": "aa-intelligence-index",
  "score": 29,
  "unit": "index",
  "provenance": "independent",
  "setting": null,
  "view": "AA leaderboard, 205 current models",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://artificialanalysis.ai/leaderboards/models"
  ]
 },
 {
  "model": "minimax-minimax-m3",
  "benchmark": "browsecomp",
  "score": 83.5,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://www.minimax.io/models/text/m3"
  ]
 },
 {
  "model": "minimax-minimax-m3",
  "benchmark": "lmarena-text",
  "score": null,
  "unit": "Elo",
  "provenance": "independent",
  "setting": null,
  "view": "Arena Text overall",
  "rank": 96,
  "rank_population": null,
  "date": "2026-10-08",
  "sources": [
   "https://arena.ai/leaderboard/chat/text"
  ]
 },
 {
  "model": "minimax-minimax-m3",
  "benchmark": "mmmu-pro",
  "score": 78.1,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/MiniMaxAI/MiniMax-M3"
  ]
 },
 {
  "model": "minimax-minimax-m3",
  "benchmark": "swe-bench-pro",
  "score": 59,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "scaffold not stated",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/MiniMaxAI/MiniMax-M3"
  ]
 },
 {
  "model": "minimax-minimax-m3",
  "benchmark": "swe-bench-verified",
  "score": 80.5,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/MiniMaxAI/MiniMax-M3"
  ]
 },
 {
  "model": "minimax-minimax-m3",
  "benchmark": "swe-bench-verified",
  "score": 80.5,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/MiniMaxAI/MiniMax-M3"
  ]
 },
 {
  "model": "minimax-music-3",
  "benchmark": "aa-music-arena-v1-1",
  "score": 1000,
  "unit": "Elo",
  "provenance": "independent",
  "setting": "secondary capture of AA post; anchor; top open weights",
  "view": "AA Music Arena v1.1, Instrumental",
  "rank": 13,
  "rank_population": null,
  "date": "2026-10",
  "sources": [
   "https://alphasignal.ai/news/artificial-analysis-music-arena-v1-1-crowns-suno-v6-across-1-000-harder-prompts",
   "https://digg.com/ai/g8egglmo"
  ]
 },
 {
  "model": "minimax-music-3",
  "benchmark": "aa-music-arena-v1-1",
  "score": 1000,
  "unit": "Elo",
  "provenance": "independent",
  "setting": "secondary capture of AA post; anchor; top open weights",
  "view": "AA Music Arena v1.1, Vocal",
  "rank": 11,
  "rank_population": null,
  "date": "2026-10",
  "sources": [
   "https://alphasignal.ai/news/artificial-analysis-music-arena-v1-1-crowns-suno-v6-across-1-000-harder-prompts",
   "https://digg.com/ai/g8egglmo"
  ]
 },
 {
  "model": "minimax-speech-2-8-hd",
  "benchmark": "aa-tts",
  "score": 1173,
  "unit": "Elo",
  "provenance": "independent",
  "setting": null,
  "view": "AA Text-to-Speech arena, 96 models",
  "rank": 19,
  "rank_population": 96,
  "date": "2026-10-10",
  "sources": [
   "https://artificialanalysis.ai/text-to-speech/leaderboard"
  ]
 },
 {
  "model": "mistral-ai-devstral-2-123b-instruct-2512",
  "benchmark": "swe-bench-multilingual",
  "score": 61.3,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/mistralai/Devstral-2-123B-Instruct-2512"
  ]
 },
 {
  "model": "mistral-ai-devstral-2-123b-instruct-2512",
  "benchmark": "swe-bench-verified",
  "score": 72.2,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/mistralai/Devstral-2-123B-Instruct-2512"
  ]
 },
 {
  "model": "mistral-ai-devstral-2-123b-instruct-2512",
  "benchmark": "terminal-bench-2-0",
  "score": 32.6,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/mistralai/Devstral-2-123B-Instruct-2512"
  ]
 },
 {
  "model": "mistral-ai-devstral-medium-1-0",
  "benchmark": "swe-bench-verified",
  "score": 61.6,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://mistral.ai/news/codestral-25-08"
  ]
 },
 {
  "model": "mistral-ai-devstral-small-1-1",
  "benchmark": "swe-bench-verified",
  "score": 53.6,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://mistral.ai/news/codestral-25-08"
  ]
 },
 {
  "model": "mistral-ai-devstral-small-2-24b-instruct-2512",
  "benchmark": "swe-bench-multilingual",
  "score": 55.7,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/mistralai/Devstral-2-123B-Instruct-2512"
  ]
 },
 {
  "model": "mistral-ai-devstral-small-2-24b-instruct-2512",
  "benchmark": "swe-bench-verified",
  "score": 68,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/mistralai/Devstral-2-123B-Instruct-2512"
  ]
 },
 {
  "model": "mistral-ai-devstral-small-2-24b-instruct-2512",
  "benchmark": "terminal-bench-2-0",
  "score": 22.5,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/mistralai/Devstral-2-123B-Instruct-2512"
  ]
 },
 {
  "model": "mistral-ai-mistral-large-3",
  "benchmark": "gpqa-diamond",
  "score": 67.17,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/mistralai/Mistral-Large-3-675B-Instruct-2512"
  ]
 },
 {
  "model": "mistral-ai-mistral-large-4",
  "benchmark": "aa-intelligence-index",
  "score": 38,
  "unit": "index",
  "provenance": "independent",
  "setting": "Mistral Large 4 Preview",
  "view": "Artificial Analysis model page",
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://artificialanalysis.ai/models/mistral-large-4"
  ]
 },
 {
  "model": "mistral-ai-mistral-large-4",
  "benchmark": "aa-intelligence-index",
  "score": 38,
  "unit": "index",
  "provenance": "independent",
  "setting": "Preview",
  "view": "AA leaderboard, 205 current models",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://artificialanalysis.ai/leaderboards/models"
  ]
 },
 {
  "model": "mistral-ai-mistral-large-4",
  "benchmark": "lmarena-text",
  "score": null,
  "unit": "Elo",
  "provenance": "independent",
  "setting": null,
  "view": "Arena Text overall",
  "rank": 115,
  "rank_population": null,
  "date": "2026-10-08",
  "sources": [
   "https://arena.ai/leaderboard/chat/text"
  ]
 },
 {
  "model": "mistral-ai-mistral-medium-3-5",
  "benchmark": "aa-intelligence-index",
  "score": 14,
  "unit": "index",
  "provenance": "independent",
  "setting": null,
  "view": "AA leaderboard, 205 current models",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://artificialanalysis.ai/leaderboards/models"
  ]
 },
 {
  "model": "mistral-ai-mistral-medium-3-5",
  "benchmark": "lmarena-text",
  "score": null,
  "unit": "Elo",
  "provenance": "independent",
  "setting": null,
  "view": "Arena Text overall",
  "rank": 117,
  "rank_population": null,
  "date": "2026-10-08",
  "sources": [
   "https://arena.ai/leaderboard/chat/text"
  ]
 },
 {
  "model": "mistral-ai-mistral-medium-3-5",
  "benchmark": "sea-helm",
  "score": 64.71,
  "unit": "score",
  "provenance": "maintainer-run",
  "setting": null,
  "view": "SEA-HELM SEA average, open-weight models",
  "rank": null,
  "rank_population": null,
  "date": "2026-09-18",
  "sources": [
   "https://leaderboard.sea-lion.ai/detailed/SEA"
  ],
  "uncertainty": "95% CI [-0.59, +0.59]"
 },
 {
  "model": "mistral-ai-mistral-medium-3-5",
  "benchmark": "sea-helm",
  "score": 70.09,
  "unit": "score",
  "provenance": "maintainer-run",
  "setting": null,
  "view": "SEA-HELM Indonesian, open-weight models, average of 2,000 bootstraps",
  "rank": 9,
  "rank_population": null,
  "date": "2026-09-18",
  "sources": [
   "https://leaderboard.sea-lion.ai/detailed/ID"
  ],
  "uncertainty": "95% CI [-1.18, +1.13]"
 },
 {
  "model": "mistral-ai-mistral-medium-3-5",
  "benchmark": "swe-bench-verified",
  "score": 77.6,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/mistralai/Mistral-Medium-3.5-128B"
  ]
 },
 {
  "model": "mistral-ai-mistral-medium-dec-23",
  "benchmark": "mt-bench",
  "score": 8.6,
  "unit": "score",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2023-12-11",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://mistral.ai/news/la-plateforme/"
  ]
 },
 {
  "model": "mistral-ai-mistral-small-4",
  "benchmark": "gpqa-diamond",
  "score": 71.2,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/mistralai/Mistral-Small-4-119B-2603"
  ]
 },
 {
  "model": "mistral-ai-mistral-small-4",
  "benchmark": "sea-helm",
  "score": 52.07,
  "unit": "score",
  "provenance": "maintainer-run",
  "setting": "Checkpoint Mistral-Small-4-119B-2603 as listed; release view (data last updated 18 Sep 2026); score is the average of 2000 bootstraps",
  "view": "SEA-HELM leaderboard, 58 models, SEA average",
  "rank": null,
  "rank_population": null,
  "date": "2026-09-18",
  "uncertainty": "95% CI [-0.61, +0.64]",
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://leaderboard.sea-lion.ai/detailed/SEA"
  ]
 },
 {
  "model": "mistral-ai-mistral-small-4",
  "benchmark": "sea-helm",
  "score": 63.14,
  "unit": "score",
  "provenance": "maintainer-run",
  "setting": "Checkpoint Mistral-Small-4-119B-2603 as listed; release view (data last updated 18 Sep 2026); score is the average of 2000 bootstraps",
  "view": "SEA-HELM leaderboard, 58 models, Indonesian (ID)",
  "rank": null,
  "rank_population": null,
  "date": "2026-09-18",
  "uncertainty": "95% CI [-1.42, +1.50]",
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://leaderboard.sea-lion.ai/detailed/ID"
  ]
 },
 {
  "model": "mistral-ai-mixtral-8x22b-instruct",
  "benchmark": "gsm8k",
  "score": 90.8,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "maj@8",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2024-04-17",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://mistral.ai/news/mixtral-8x22b/"
  ]
 },
 {
  "model": "mistral-ai-mixtral-8x22b-instruct",
  "benchmark": "math",
  "score": 44.6,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "maj@4",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2024-04-17",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://mistral.ai/news/mixtral-8x22b/"
  ]
 },
 {
  "model": "mistral-ai-pixtral-large",
  "benchmark": "ai2d",
  "score": 93.8,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "BBox",
  "view": "Pixtral Large model card",
  "rank": null,
  "rank_population": null,
  "date": "2024-11-18",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://huggingface.co/mistralai/Pixtral-Large-Instruct-2411"
  ]
 },
 {
  "model": "mistral-ai-pixtral-large",
  "benchmark": "mmmu",
  "score": 64,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "CoT",
  "view": "Pixtral Large model card",
  "rank": null,
  "rank_population": null,
  "date": "2024-11-18",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://huggingface.co/mistralai/Pixtral-Large-Instruct-2411"
  ]
 },
 {
  "model": "mistral-ai-shieldstral-1-0-3b",
  "benchmark": "harmbench",
  "score": 99.4,
  "unit": "F1",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/mistralai/Shieldstral-1.0-3B"
  ]
 },
 {
  "model": "mistral-ai-shieldstral-1-0-3b",
  "benchmark": "polyguard",
  "score": 84.6,
  "unit": "F1",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/mistralai/Shieldstral-1.0-3B"
  ]
 },
 {
  "model": "mistral-ai-shieldstral-1-0-3b",
  "benchmark": "vlguard",
  "score": 97.7,
  "unit": "F1",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/mistralai/Shieldstral-1.0-3B"
  ]
 },
 {
  "model": "mistral-ai-shieldstral-1-0-3b",
  "benchmark": "wildguardtest",
  "score": 88.1,
  "unit": "F1",
  "provenance": "vendor-reported",
  "setting": "prompt",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/mistralai/Shieldstral-1.0-3B"
  ]
 },
 {
  "model": "mistral-ai-shieldstral-1-0-3b",
  "benchmark": "xstest",
  "score": 94.6,
  "unit": "F1",
  "provenance": "vendor-reported",
  "setting": "refusal",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/mistralai/Shieldstral-1.0-3B"
  ]
 },
 {
  "model": "mistral-ai-voxtral-small",
  "benchmark": "open-asr-leaderboard",
  "score": 6.62,
  "unit": "WER",
  "provenance": "maintainer-run",
  "setting": "average WER",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://select.keenable.ai/r/speech-recognition-accuracy-leaders-2022-2026/JbURQjlVooLQ6J10NkbRVw"
  ]
 },
 {
  "model": "mit-han-lab-mcunet-in4",
  "benchmark": "imagenet",
  "score": 68,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "int8, top-1",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://github.com/mit-han-lab/mcunet"
  ],
  "unverified": []
 },
 {
  "model": "mit-han-lab-mcunet-vww2",
  "benchmark": "visual-wake-words",
  "score": 91.8,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "int8",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://github.com/mit-han-lab/mcunet"
  ],
  "unverified": []
 },
 {
  "model": "moonshot-ai-kimi-k2-5",
  "benchmark": "swe-bench-verified",
  "score": 76.8,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://leaderboard.steel.dev/leaderboards/swe-bench-verified.md"
  ]
 },
 {
  "model": "moonshot-ai-kimi-k2-6",
  "benchmark": "lmarena-text",
  "score": 1461,
  "unit": "Elo",
  "provenance": "independent",
  "setting": null,
  "view": "Arena Text overall",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-08",
  "sources": [
   "https://arena.ai/leaderboard/chat/text"
  ],
  "uncertainty": "±4"
 },
 {
  "model": "moonshot-ai-kimi-k2-6",
  "benchmark": "swe-bench-verified",
  "score": 80.2,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://leaderboard.steel.dev/leaderboards/swe-bench-verified.md"
  ]
 },
 {
  "model": "moonshot-ai-kimi-k2-7-code",
  "benchmark": "kimi-code-bench-v2",
  "score": 62,
  "unit": null,
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/moonshotai/Kimi-K2.7-Code"
  ]
 },
 {
  "model": "moonshot-ai-kimi-k2-7-code",
  "benchmark": "programbench",
  "score": 53.6,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "Kimi Code CLI, thinking",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/moonshotai/Kimi-K2.7-Code"
  ]
 },
 {
  "model": "moonshot-ai-kimi-k3",
  "benchmark": "aa-intelligence-index",
  "score": 44,
  "unit": "index",
  "provenance": "independent",
  "setting": "Kimi K3 (Max)",
  "view": "Artificial Analysis open-weights view",
  "rank": 3,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://artificialanalysis.ai/leaderboards/models?open_weights=true",
   "https://artificialanalysis.ai/models/open-source"
  ]
 },
 {
  "model": "moonshot-ai-kimi-k3",
  "benchmark": "aa-intelligence-index",
  "score": 44,
  "unit": "index",
  "provenance": "independent",
  "setting": "max",
  "view": "AA leaderboard, 205 current models",
  "rank": 31,
  "rank_population": 205,
  "date": "2026-10-10",
  "sources": [
   "https://artificialanalysis.ai/leaderboards/models"
  ]
 },
 {
  "model": "moonshot-ai-kimi-k3",
  "benchmark": "browsecomp",
  "score": 91.2,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/moonshotai/Kimi-K3"
  ]
 },
 {
  "model": "moonshot-ai-kimi-k3",
  "benchmark": "deepswe",
  "score": 67.5,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "Kimi Code harness; 67.3 with mini-SWE-agent",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/moonshotai/Kimi-K3"
  ]
 },
 {
  "model": "moonshot-ai-kimi-k3",
  "benchmark": "frontierswe",
  "score": 81.2,
  "unit": null,
  "provenance": "vendor-reported",
  "setting": "Kimi Code harness",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/moonshotai/Kimi-K3"
  ]
 },
 {
  "model": "moonshot-ai-kimi-k3",
  "benchmark": "gpqa-diamond",
  "score": 93.5,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/moonshotai/Kimi-K3"
  ]
 },
 {
  "model": "moonshot-ai-kimi-k3",
  "benchmark": "hle",
  "score": 43.5,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "without tools",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/moonshotai/Kimi-K3"
  ]
 },
 {
  "model": "moonshot-ai-kimi-k3",
  "benchmark": "hle",
  "score": 56,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "with tools",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/moonshotai/Kimi-K3"
  ]
 },
 {
  "model": "moonshot-ai-kimi-k3",
  "benchmark": "lmarena-text",
  "score": 1488,
  "unit": "Elo",
  "provenance": "independent",
  "setting": "kimi-k3-max; top open model",
  "view": "Arena Text overall",
  "rank": 16,
  "rank_population": null,
  "date": "2026-10-08",
  "sources": [
   "https://arena.ai/leaderboard/chat/text"
  ],
  "uncertainty": "±5"
 },
 {
  "model": "moonshot-ai-kimi-k3",
  "benchmark": "osworld-verified",
  "score": 84.8,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/moonshotai/Kimi-K3"
  ]
 },
 {
  "model": "moonshot-ai-kimi-k3",
  "benchmark": "programbench",
  "score": 77.8,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "Kimi Code harness",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/moonshotai/Kimi-K3"
  ]
 },
 {
  "model": "moonshot-ai-kimi-k3",
  "benchmark": "swe-marathon",
  "score": 42,
  "unit": null,
  "provenance": "vendor-reported",
  "setting": "Claude Code harness",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/moonshotai/Kimi-K3"
  ]
 },
 {
  "model": "moonshot-ai-kimi-k3",
  "benchmark": "terminal-bench-2-1",
  "score": 88.3,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/moonshotai/Kimi-K3"
  ]
 },
 {
  "model": "moonshot-ai-kimi-k3",
  "benchmark": "terminal-bench-2-1",
  "score": 88.3,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "Kimi Code harness",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/moonshotai/Kimi-K3"
  ]
 },
 {
  "model": "morgan-stanley-lag-llama",
  "benchmark": "gift-eval",
  "score": 0.88,
  "unit": "CRPS (geo-mean, normalised to Seasonal Naive)",
  "provenance": "independent",
  "setting": "pretrained, test leakage Yes; rank is average CRPS rank",
  "view": "Leaderboard rebuilt from the published raw results, 143 entries covering all 97 configurations",
  "rank": 136,
  "rank_population": 143,
  "date": "2026-10-09",
  "sources": [
   "https://huggingface.co/spaces/Salesforce/GIFT-Eval"
  ],
  "leakage": "yes",
  "leakage_note": "Test Leak. column: Yes (Lag-Llama)"
 },
 {
  "model": "morgan-stanley-lag-llama",
  "benchmark": "gift-eval",
  "score": 1.228,
  "unit": "MASE (geo-mean, normalised to Seasonal Naive)",
  "provenance": "independent",
  "setting": "pretrained, test leakage Yes",
  "view": "Leaderboard rebuilt from the published raw results, 143 entries covering all 97 configurations",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-09",
  "sources": [
   "https://huggingface.co/spaces/Salesforce/GIFT-Eval"
  ],
  "leakage": "yes",
  "leakage_note": "Test Leak. column: Yes (Lag-Llama)"
 },
 {
  "model": "motif-technologies-motif-3",
  "benchmark": "aa-lcr-v1-1",
  "score": 72.3,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "temperature 1.0, top-p 0.95, max sequence 262,144; AA-LCR",
  "view": "Motif-3 model card",
  "rank": null,
  "rank_population": null,
  "date": "2026-08",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://huggingface.co/Motif-Technologies/Motif-3"
  ]
 },
 {
  "model": "motif-technologies-motif-3",
  "benchmark": "critpt",
  "score": 6.6,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "temperature 1.0, top-p 0.95, max sequence 262,144",
  "view": "Motif-3 model card",
  "rank": null,
  "rank_population": null,
  "date": "2026-08",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://huggingface.co/Motif-Technologies/Motif-3"
  ]
 },
 {
  "model": "motif-technologies-motif-3",
  "benchmark": "gpqa-diamond",
  "score": 83.4,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "temperature 1.0, top-p 0.95, max sequence 262,144",
  "view": "Motif-3 model card",
  "rank": null,
  "rank_population": null,
  "date": "2026-08",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://huggingface.co/Motif-Technologies/Motif-3"
  ]
 },
 {
  "model": "motif-technologies-motif-3",
  "benchmark": "hle",
  "score": 37,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "temperature 1.0, top-p 0.95, max sequence 262,144",
  "view": "Motif-3 model card",
  "rank": null,
  "rank_population": null,
  "date": "2026-08",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://huggingface.co/Motif-Technologies/Motif-3"
  ]
 },
 {
  "model": "motif-technologies-motif-3",
  "benchmark": "ifbench",
  "score": 78.2,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "temperature 1.0, top-p 0.95, max sequence 262,144",
  "view": "Motif-3 model card",
  "rank": null,
  "rank_population": null,
  "date": "2026-08",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://huggingface.co/Motif-Technologies/Motif-3"
  ]
 },
 {
  "model": "motif-technologies-motif-3",
  "benchmark": "scicode",
  "score": 40.6,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "temperature 1.0, top-p 0.95, max sequence 262,144",
  "view": "Motif-3 model card",
  "rank": null,
  "rank_population": null,
  "date": "2026-08",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://huggingface.co/Motif-Technologies/Motif-3"
  ]
 },
 {
  "model": "motif-technologies-motif-3",
  "benchmark": "swe-bench-verified",
  "score": 76.2,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "temperature 1.0, top-p 0.95, max sequence 262,144",
  "view": "Motif-3 model card",
  "rank": null,
  "rank_population": null,
  "date": "2026-08",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://huggingface.co/Motif-Technologies/Motif-3"
  ]
 },
 {
  "model": "motif-technologies-motif-3",
  "benchmark": "tau2-bench",
  "score": 94.7,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "temperature 1.0, top-p 0.95, max sequence 262,144; Telecom",
  "view": "Motif-3 model card",
  "rank": null,
  "rank_population": null,
  "date": "2026-08",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://huggingface.co/Motif-Technologies/Motif-3"
  ]
 },
 {
  "model": "motif-technologies-motif-3",
  "benchmark": "terminal-bench-2-1",
  "score": 74.9,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "temperature 1.0, top-p 0.95, max sequence 262,144",
  "view": "Motif-3 model card",
  "rank": null,
  "rank_population": null,
  "date": "2026-08",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://huggingface.co/Motif-Technologies/Motif-3"
  ]
 },
 {
  "model": "mscred",
  "benchmark": "skab",
  "score": 32.42,
  "unit": "NAB score",
  "provenance": "maintainer-run",
  "setting": "Changepoint detection leaderboard",
  "view": null,
  "rank": 1,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://github.com/waico/SKAB"
  ]
 },
 {
  "model": "mset",
  "benchmark": "skab",
  "score": 0.78,
  "unit": "F1",
  "provenance": "maintainer-run",
  "setting": "Outlier detection leaderboard",
  "view": null,
  "rank": 1,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://github.com/waico/SKAB"
  ]
 },
 {
  "model": "mureka-v9-5",
  "benchmark": "aa-music-arena-v1-1",
  "score": 1080,
  "unit": "Elo",
  "provenance": "independent",
  "setting": "secondary capture of AA post; tied 3-6",
  "view": "AA Music Arena v1.1, Instrumental",
  "rank": 3,
  "rank_population": null,
  "date": "2026-10",
  "sources": [
   "https://alphasignal.ai/news/artificial-analysis-music-arena-v1-1-crowns-suno-v6-across-1-000-harder-prompts",
   "https://digg.com/ai/g8egglmo"
  ]
 },
 {
  "model": "mureka-v9-5",
  "benchmark": "aa-music-arena-v1-1",
  "score": 1103,
  "unit": "Elo",
  "provenance": "independent",
  "setting": "secondary capture of AA post",
  "view": "AA Music Arena v1.1, Vocal",
  "rank": 3,
  "rank_population": null,
  "date": "2026-10",
  "sources": [
   "https://alphasignal.ai/news/artificial-analysis-music-arena-v1-1-crowns-suno-v6-across-1-000-harder-prompts",
   "https://digg.com/ai/g8egglmo"
  ]
 },
 {
  "model": "mureka-v9",
  "benchmark": "aa-music-arena-v1-1",
  "score": 1081,
  "unit": "Elo",
  "provenance": "independent",
  "setting": "secondary capture of AA post; tied 3-6",
  "view": "AA Music Arena v1.1, Instrumental",
  "rank": 3,
  "rank_population": null,
  "date": "2026-10",
  "sources": [
   "https://alphasignal.ai/news/artificial-analysis-music-arena-v1-1-crowns-suno-v6-across-1-000-harder-prompts",
   "https://digg.com/ai/g8egglmo"
  ]
 },
 {
  "model": "naver-hyperclova-x-seed-think-32b",
  "benchmark": "aa-intelligence-index",
  "score": 11,
  "unit": "index",
  "provenance": "independent",
  "setting": "asterisk on page",
  "view": "AA leaderboard, 205 current models",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://artificialanalysis.ai/leaderboards/models"
  ]
 },
 {
  "model": "neuralgcm",
  "benchmark": "weatherbench-2",
  "score": 115.7,
  "unit": "RMSE m2/s2",
  "provenance": "maintainer-run",
  "setting": "Z500 day 3, deterministic, NeuralGCM 0.7 vs ERA5",
  "view": "year 2020, 240x121 grid",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://researchsites.withgoogle.com/weatherbench/deterministic/"
  ]
 },
 {
  "model": "neuralgcm",
  "benchmark": "weatherbench-2",
  "score": 126.2,
  "unit": "RMSE m2/s2",
  "provenance": "maintainer-run",
  "setting": "Z500 day 3, deterministic, NeuralGCM ENS (mean) vs ERA5",
  "view": "year 2020, 240x121 grid",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://researchsites.withgoogle.com/weatherbench/deterministic/"
  ]
 },
 {
  "model": "neuralgcm",
  "benchmark": "weatherbench-2",
  "score": 266.2,
  "unit": "RMSE m2/s2",
  "provenance": "maintainer-run",
  "setting": "Z500 day 5, deterministic, NeuralGCM ENS (mean) vs ERA5",
  "view": "year 2020, 240x121 grid",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://researchsites.withgoogle.com/weatherbench/deterministic/"
  ]
 },
 {
  "model": "neuralgcm",
  "benchmark": "weatherbench-2",
  "score": 267.1,
  "unit": "RMSE m2/s2",
  "provenance": "maintainer-run",
  "setting": "Z500 day 5, deterministic, NeuralGCM 0.7 vs ERA5",
  "view": "year 2020, 240x121 grid",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://researchsites.withgoogle.com/weatherbench/deterministic/"
  ]
 },
 {
  "model": "neuralgcm",
  "benchmark": "weatherbench-2",
  "score": 37.9,
  "unit": "RMSE m2/s2",
  "provenance": "maintainer-run",
  "setting": "Z500 day 1, deterministic, NeuralGCM 0.7 vs ERA5",
  "view": "year 2020, 240x121 grid",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://researchsites.withgoogle.com/weatherbench/deterministic/"
  ]
 },
 {
  "model": "neuralgcm",
  "benchmark": "weatherbench-2",
  "score": 44,
  "unit": "RMSE m2/s2",
  "provenance": "maintainer-run",
  "setting": "Z500 day 1, deterministic, NeuralGCM ENS (mean) vs ERA5",
  "view": "year 2020, 240x121 grid",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://researchsites.withgoogle.com/weatherbench/deterministic/"
  ]
 },
 {
  "model": "neuralgcm",
  "benchmark": "weatherbench-2",
  "score": 606.8,
  "unit": "RMSE m2/s2",
  "provenance": "maintainer-run",
  "setting": "Z500 day 10, deterministic, NeuralGCM ENS (mean) vs ERA5",
  "view": "year 2020, 240x121 grid",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://researchsites.withgoogle.com/weatherbench/deterministic/"
  ]
 },
 {
  "model": "neuralgcm",
  "benchmark": "weatherbench-2",
  "score": 751.4,
  "unit": "RMSE m2/s2",
  "provenance": "maintainer-run",
  "setting": "Z500 day 10, deterministic, NeuralGCM 0.7 vs ERA5",
  "view": "year 2020, 240x121 grid",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://researchsites.withgoogle.com/weatherbench/deterministic/"
  ]
 },
 {
  "model": "numenta-htm",
  "benchmark": "nab",
  "score": 70.5,
  "unit": "NAB score",
  "provenance": "maintainer-run",
  "setting": "Standard profile; Numenta HTM entries range 70.5 to 69.7",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://github.com/numenta/NAB"
  ]
 },
 {
  "model": "nvidia-canary-1b-flash",
  "benchmark": "open-asr-leaderboard",
  "score": 6.35,
  "unit": "WER",
  "provenance": "maintainer-run",
  "setting": "eight-set macro-average English WER",
  "view": "snapshot 2026-05-06 via benchmarklist",
  "rank": null,
  "rank_population": null,
  "date": "2026-05-06",
  "sources": [
   "https://benchmarklist.com/benchmarks/open_asr_leaderboard/"
  ]
 },
 {
  "model": "nvidia-canary-1b",
  "benchmark": "open-asr-leaderboard",
  "score": 6.5,
  "unit": "WER",
  "provenance": "maintainer-run",
  "setting": "eight-set macro-average English WER",
  "view": "snapshot 2026-05-06 via benchmarklist",
  "rank": null,
  "rank_population": null,
  "date": "2026-05-06",
  "sources": [
   "https://benchmarklist.com/benchmarks/open_asr_leaderboard/"
  ]
 },
 {
  "model": "nvidia-canary-qwen-2-5b",
  "benchmark": "open-asr-leaderboard",
  "score": 5.63,
  "unit": "WER",
  "provenance": "maintainer-run",
  "setting": "eight-set macro-average English WER",
  "view": "snapshot 2026-05-06 via benchmarklist",
  "rank": null,
  "rank_population": null,
  "date": "2026-05-06",
  "sources": [
   "https://benchmarklist.com/benchmarks/open_asr_leaderboard/"
  ]
 },
 {
  "model": "nvidia-llama-3-1-nemotron-70b-instruct",
  "benchmark": "lmarena-text",
  "score": 1267,
  "unit": "Elo",
  "provenance": "vendor-reported",
  "setting": "Chatbot Arena score quoted by NVIDIA on the model card; style controlled rank 26",
  "view": "Chatbot Arena leaderboard as of 24 Oct 2024",
  "rank": 9,
  "rank_population": null,
  "date": "2024-10-24",
  "uncertainty": "+-7",
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://huggingface.co/nvidia/Llama-3.1-Nemotron-70B-Instruct-HF"
  ]
 },
 {
  "model": "nvidia-llama-3-1-nemotron-ultra-253b-v1",
  "benchmark": "aime-2025",
  "score": 72.5,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "Reasoning on, pass@1",
  "view": "Nemotron Ultra model card",
  "rank": null,
  "rank_population": null,
  "date": "2025-04",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://huggingface.co/nvidia/Llama-3_1-Nemotron-Ultra-253B-v1"
  ]
 },
 {
  "model": "nvidia-llama-3-1-nemotron-ultra-253b-v1",
  "benchmark": "gpqa",
  "score": 76.01,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "Reasoning on, pass@1",
  "view": "Nemotron Ultra model card",
  "rank": null,
  "rank_population": null,
  "date": "2025-04",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://huggingface.co/nvidia/Llama-3_1-Nemotron-Ultra-253B-v1"
  ]
 },
 {
  "model": "nvidia-llama-3-1-nemotron-ultra-253b-v1",
  "benchmark": "ifeval",
  "score": 89.45,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "Reasoning on, strict instruction",
  "view": "Nemotron Ultra model card",
  "rank": null,
  "rank_population": null,
  "date": "2025-04",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://huggingface.co/nvidia/Llama-3_1-Nemotron-Ultra-253B-v1"
  ]
 },
 {
  "model": "nvidia-llama-3-1-nemotron-ultra-253b-v1",
  "benchmark": "livecodebench",
  "score": 66.31,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "Reasoning on, 2024-08-01 to 2025-02-01 window",
  "view": "Nemotron Ultra model card",
  "rank": null,
  "rank_population": null,
  "date": "2025-04",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://huggingface.co/nvidia/Llama-3_1-Nemotron-Ultra-253B-v1"
  ]
 },
 {
  "model": "nvidia-llama-3-1-nemotron-ultra-253b-v1",
  "benchmark": "math-500",
  "score": 97,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "Reasoning on, pass@1",
  "view": "Nemotron Ultra model card",
  "rank": null,
  "rank_population": null,
  "date": "2025-04",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://huggingface.co/nvidia/Llama-3_1-Nemotron-Ultra-253B-v1"
  ]
 },
 {
  "model": "nvidia-llama-3-3-nemotron-super-49b-v1",
  "benchmark": "aime-2025",
  "score": 58.4,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "Reasoning on, pass@1",
  "view": "Nemotron Super model card",
  "rank": null,
  "rank_population": null,
  "date": "2025-03",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://huggingface.co/nvidia/Llama-3_3-Nemotron-Super-49B-v1"
  ]
 },
 {
  "model": "nvidia-llama-3-3-nemotron-super-49b-v1",
  "benchmark": "gpqa",
  "score": 66.67,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "Reasoning on",
  "view": "Nemotron Super model card",
  "rank": null,
  "rank_population": null,
  "date": "2025-03",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://huggingface.co/nvidia/Llama-3_3-Nemotron-Super-49B-v1"
  ]
 },
 {
  "model": "nvidia-llama-3-3-nemotron-super-49b-v1",
  "benchmark": "ifeval",
  "score": 89.21,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "Reasoning off, strict instruction",
  "view": "Nemotron Super model card",
  "rank": null,
  "rank_population": null,
  "date": "2025-03",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://huggingface.co/nvidia/Llama-3_3-Nemotron-Super-49B-v1"
  ]
 },
 {
  "model": "nvidia-llama-3-3-nemotron-super-49b-v1",
  "benchmark": "math-500",
  "score": 96.6,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "Reasoning on, pass@1",
  "view": "Nemotron Super model card",
  "rank": null,
  "rank_population": null,
  "date": "2025-03",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://huggingface.co/nvidia/Llama-3_3-Nemotron-Super-49B-v1"
  ]
 },
 {
  "model": "nvidia-nemotron-3-5-content-safety",
  "benchmark": "aegis-2-0",
  "score": 0.86,
  "unit": "F1",
  "provenance": "vendor-reported",
  "setting": "prompt",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/nvidia/Nemotron-3.5-Content-Safety"
  ]
 },
 {
  "model": "nvidia-nemotron-3-5-content-safety",
  "benchmark": "multijail",
  "score": 0.95,
  "unit": "F1",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/nvidia/Nemotron-3.5-Content-Safety"
  ]
 },
 {
  "model": "nvidia-nemotron-3-5-content-safety",
  "benchmark": "polyguard",
  "score": 0.8,
  "unit": "F1",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/nvidia/Nemotron-3.5-Content-Safety"
  ]
 },
 {
  "model": "nvidia-nemotron-3-5-content-safety",
  "benchmark": "wildguardtest",
  "score": 0.85,
  "unit": "F1",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/nvidia/Nemotron-3.5-Content-Safety"
  ]
 },
 {
  "model": "nvidia-nemotron-3-5-lightning-30b-a3b",
  "benchmark": "sea-helm",
  "score": 46.06,
  "unit": "score",
  "provenance": "maintainer-run",
  "setting": null,
  "view": "SEA-HELM SEA average, open-weight models",
  "rank": null,
  "rank_population": null,
  "date": "2026-09-18",
  "sources": [
   "https://leaderboard.sea-lion.ai/detailed/SEA"
  ],
  "uncertainty": "95% CI [-0.54, +0.54]"
 },
 {
  "model": "nvidia-nemotron-3-5-lightning-30b-a3b",
  "benchmark": "sea-helm",
  "score": 64.34,
  "unit": "score",
  "provenance": "maintainer-run",
  "setting": null,
  "view": "SEA-HELM Indonesian, open-weight models, average of 2,000 bootstraps",
  "rank": null,
  "rank_population": null,
  "date": "2026-09-18",
  "sources": [
   "https://leaderboard.sea-lion.ai/detailed/ID"
  ],
  "uncertainty": "95% CI [-1.36, +1.37]"
 },
 {
  "model": "nvidia-nemotron-3-embed-8b",
  "benchmark": "mmteb",
  "score": 75.45,
  "unit": "score",
  "provenance": "vendor-reported",
  "setting": "retrieval",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/nvidia/Nemotron-3-Embed-8B-BF16"
  ]
 },
 {
  "model": "nvidia-nemotron-3-embed-8b",
  "benchmark": "rteb",
  "score": 78.46,
  "unit": "score",
  "provenance": "vendor-reported",
  "setting": null,
  "view": "Claims #1 on RTEB",
  "rank": 1,
  "rank_population": null,
  "date": "2026-07-16",
  "sources": [
   "https://huggingface.co/nvidia/Nemotron-3-Embed-8B-BF16"
  ]
 },
 {
  "model": "nvidia-nemotron-3-nano-30b-a3b",
  "benchmark": "sea-helm",
  "score": 46.89,
  "unit": "score",
  "provenance": "maintainer-run",
  "setting": "Checkpoint NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 as listed; release view (data last updated 18 Sep 2026); score is the average of 2000 bootstraps",
  "view": "SEA-HELM leaderboard, 58 models, SEA average",
  "rank": null,
  "rank_population": null,
  "date": "2026-09-18",
  "uncertainty": "95% CI [-0.50, +0.55]",
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://leaderboard.sea-lion.ai/detailed/SEA"
  ]
 },
 {
  "model": "nvidia-nemotron-3-nano-30b-a3b",
  "benchmark": "sea-helm",
  "score": 65.36,
  "unit": "score",
  "provenance": "maintainer-run",
  "setting": "Checkpoint NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 as listed; release view (data last updated 18 Sep 2026); score is the average of 2000 bootstraps",
  "view": "SEA-HELM leaderboard, 58 models, Indonesian (ID)",
  "rank": null,
  "rank_population": null,
  "date": "2026-09-18",
  "uncertainty": "95% CI [-1.30, +1.30]",
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://leaderboard.sea-lion.ai/detailed/ID"
  ]
 },
 {
  "model": "nvidia-nemotron-3-super",
  "benchmark": "sea-helm",
  "score": 49.3,
  "unit": "score",
  "provenance": "maintainer-run",
  "setting": null,
  "view": "SEA-HELM SEA average, open-weight models",
  "rank": null,
  "rank_population": null,
  "date": "2026-09-18",
  "sources": [
   "https://leaderboard.sea-lion.ai/detailed/SEA"
  ],
  "uncertainty": "95% CI [-0.51, +0.53]"
 },
 {
  "model": "nvidia-nemotron-3-super",
  "benchmark": "sea-helm",
  "score": 70.78,
  "unit": "score",
  "provenance": "maintainer-run",
  "setting": null,
  "view": "SEA-HELM Indonesian, open-weight models, average of 2,000 bootstraps",
  "rank": 8,
  "rank_population": null,
  "date": "2026-09-18",
  "sources": [
   "https://leaderboard.sea-lion.ai/detailed/ID"
  ],
  "uncertainty": "95% CI [-1.22, +1.20]"
 },
 {
  "model": "nvidia-nemotron-3-ultra",
  "benchmark": "aa-intelligence-index",
  "score": 23,
  "unit": "index",
  "provenance": "independent",
  "setting": "Nemotron 3 Ultra 550B A55B Reasoning",
  "view": "Artificial Analysis open-weights model page",
  "rank": 36,
  "rank_population": 117,
  "date": null,
  "sources": [
   "https://artificialanalysis.ai/models/nvidia-nemotron-3-ultra-550b-a55b",
   "https://artificialanalysis.ai/models/open-source"
  ]
 },
 {
  "model": "nvidia-nemotron-3-ultra",
  "benchmark": "aa-intelligence-index",
  "score": 23,
  "unit": "index",
  "provenance": "independent",
  "setting": "Reasoning",
  "view": "AA leaderboard, 205 current models",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://artificialanalysis.ai/leaderboards/models"
  ]
 },
 {
  "model": "nvidia-nemotron-3-ultra",
  "benchmark": "aa-intelligence-index",
  "score": 23,
  "unit": "index",
  "provenance": "independent",
  "setting": "Reasoning",
  "view": "AA open-weights view, 117 models",
  "rank": 36,
  "rank_population": 117,
  "date": "2026-10-10",
  "sources": [
   "https://artificialanalysis.ai/models/nvidia-nemotron-3-ultra-550b-a55b"
  ]
 },
 {
  "model": "nvidia-nemotron-3-ultra",
  "benchmark": "gpqa",
  "score": 87,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16"
  ]
 },
 {
  "model": "nvidia-nemotron-3-ultra",
  "benchmark": "mmlu-pro",
  "score": 86.8,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16"
  ]
 },
 {
  "model": "nvidia-nemotron-3-ultra",
  "benchmark": "ruler",
  "score": 94.7,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "at 1M context",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16"
  ]
 },
 {
  "model": "nvidia-nemotron-3-ultra",
  "benchmark": "swe-bench-verified",
  "score": 70.7,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16"
  ]
 },
 {
  "model": "nvidia-nemotron-3-ultra",
  "benchmark": "swe-bench-verified",
  "score": 70.7,
  "unit": "%",
  "provenance": "independent",
  "setting": "third-party",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://leaderboard.steel.dev/leaderboards/swe-bench-verified.md"
  ]
 },
 {
  "model": "nvidia-nemotron-4-340b",
  "benchmark": "gsm8k",
  "score": 92.3,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "Instruct model; 0-shot",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2024-06",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct"
  ]
 },
 {
  "model": "nvidia-nemotron-4-340b",
  "benchmark": "humaneval",
  "score": 73.2,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "Instruct model; 0-shot",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2024-06",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct"
  ]
 },
 {
  "model": "nvidia-nemotron-4-340b",
  "benchmark": "ifeval",
  "score": 79.9,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "Instruct model; prompt-strict accuracy",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2024-06",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct"
  ]
 },
 {
  "model": "nvidia-nemotron-4-340b",
  "benchmark": "mmlu",
  "score": 78.7,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "Instruct model; 0-shot",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2024-06",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct"
  ]
 },
 {
  "model": "nvidia-nemotron-4-340b",
  "benchmark": "mt-bench",
  "score": 8.22,
  "unit": "score",
  "provenance": "vendor-reported",
  "setting": "Instruct model; judged by GPT-4-0125-Preview",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2024-06",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://huggingface.co/nvidia/Nemotron-4-340B-Instruct"
  ]
 },
 {
  "model": "nvidia-parakeet-tdt-0-6b-v2",
  "benchmark": "open-asr-leaderboard",
  "score": 6.05,
  "unit": "WER",
  "provenance": "maintainer-run",
  "setting": "eight-set macro-average English WER",
  "view": "snapshot 2026-05-06 via benchmarklist",
  "rank": null,
  "rank_population": null,
  "date": "2026-05-06",
  "sources": [
   "https://benchmarklist.com/benchmarks/open_asr_leaderboard/"
  ]
 },
 {
  "model": "nvidia-parakeet-tdt-0-6b-v3",
  "benchmark": "open-asr-leaderboard",
  "score": 6.32,
  "unit": "WER",
  "provenance": "maintainer-run",
  "setting": "eight-set macro-average English WER",
  "view": "snapshot 2026-05-06 via benchmarklist",
  "rank": null,
  "rank_population": null,
  "date": "2026-05-06",
  "sources": [
   "https://benchmarklist.com/benchmarks/open_asr_leaderboard/"
  ]
 },
 {
  "model": "nx-ai-tirex-2",
  "benchmark": "gift-eval",
  "score": 0.467,
  "unit": "CRPS (geo-mean, normalised to Seasonal Naive)",
  "provenance": "independent",
  "setting": "pretrained; rank is average CRPS rank",
  "view": "Leaderboard rebuilt from the published raw results, 143 entries covering all 97 configurations",
  "rank": 45,
  "rank_population": 143,
  "date": "2026-10-09",
  "sources": [
   "https://huggingface.co/spaces/Salesforce/GIFT-Eval"
  ],
  "leakage": "no",
  "leakage_note": "Test Leak. column: No (TiRex-2-Pretrained (code))"
 },
 {
  "model": "nx-ai-tirex-2",
  "benchmark": "gift-eval",
  "score": 0.678,
  "unit": "MASE (geo-mean, normalised to Seasonal Naive)",
  "provenance": "independent",
  "setting": "pretrained",
  "view": "Leaderboard rebuilt from the published raw results, 143 entries covering all 97 configurations",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-09",
  "sources": [
   "https://huggingface.co/spaces/Salesforce/GIFT-Eval"
  ],
  "leakage": "no",
  "leakage_note": "Test Leak. column: No (TiRex-2-Pretrained (code))"
 },
 {
  "model": "nx-ai-tirex",
  "benchmark": "gift-eval",
  "score": 0.488,
  "unit": "CRPS (geo-mean, normalised to Seasonal Naive)",
  "provenance": "independent",
  "setting": "zero-shot; rank is average CRPS rank",
  "view": "Leaderboard rebuilt from the published raw results, 143 entries covering all 97 configurations",
  "rank": 62,
  "rank_population": 143,
  "date": "2026-10-09",
  "sources": [
   "https://huggingface.co/spaces/Salesforce/GIFT-Eval"
  ],
  "leakage": "no",
  "leakage_note": "Test Leak. column: No (TiRex (code))"
 },
 {
  "model": "nx-ai-tirex",
  "benchmark": "gift-eval",
  "score": 0.716,
  "unit": "MASE (geo-mean, normalised to Seasonal Naive)",
  "provenance": "independent",
  "setting": "zero-shot",
  "view": "Leaderboard rebuilt from the published raw results, 143 entries covering all 97 configurations",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-09",
  "sources": [
   "https://huggingface.co/spaces/Salesforce/GIFT-Eval"
  ],
  "leakage": "no",
  "leakage_note": "Test Leak. column: No (TiRex (code))"
 },
 {
  "model": "nx-ai-tirex",
  "benchmark": "gift-eval",
  "score": 23.9,
  "unit": "mean CRPS rank",
  "provenance": "vendor-reported",
  "setting": "zero-shot foundation-model CRPS rank, lower is better",
  "view": "Toto 2.0 report (Datadog)",
  "rank": null,
  "rank_population": null,
  "date": "2026-06",
  "sources": [
   "https://arxiv.org/pdf/2605.20119"
  ]
 },
 {
  "model": "omnianomaly",
  "benchmark": "tsb-ad",
  "score": 0.31,
  "unit": "VUS-PR",
  "provenance": "maintainer-run",
  "setting": "Multivariate",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://github.com/TheDatumOrg/TSB-AD"
  ]
 },
 {
  "model": "openai-gpt-4",
  "benchmark": "convfinqa",
  "score": 76.48,
  "unit": "score",
  "provenance": "independent",
  "setting": "few-shot",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2023-05",
  "sources": [
   "https://arxiv.org/html/2305.05862v2"
  ]
 },
 {
  "model": "openai-gpt-4",
  "benchmark": "fiqa-sentiment",
  "score": 88.11,
  "unit": "score",
  "provenance": "independent",
  "setting": "few-shot",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2023-05",
  "sources": [
   "https://arxiv.org/html/2305.05862v2"
  ]
 },
 {
  "model": "openai-gpt-4",
  "benchmark": "gaia",
  "score": 15,
  "unit": "%",
  "provenance": "maintainer-run",
  "setting": "GPT-4 with plugins, at benchmark release",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2023-11",
  "sources": [
   "https://arxiv.org/abs/2311.12983"
  ]
 },
 {
  "model": "openai-gpt-5-3-codex",
  "benchmark": "osworld-verified",
  "score": 64.7,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "xhigh",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2026-02-05",
  "sources": [
   "https://openai.com/index/introducing-gpt-5-3-codex"
  ]
 },
 {
  "model": "openai-gpt-5-3-codex",
  "benchmark": "swe-bench-pro",
  "score": 56.8,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "xhigh",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2026-02-05",
  "sources": [
   "https://openai.com/index/introducing-gpt-5-3-codex"
  ]
 },
 {
  "model": "openai-gpt-5-3-codex",
  "benchmark": "swe-lancer-ic-diamond",
  "score": 81.4,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "xhigh",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2026-02-05",
  "sources": [
   "https://openai.com/index/introducing-gpt-5-3-codex"
  ]
 },
 {
  "model": "openai-gpt-5-3-codex",
  "benchmark": "terminal-bench-2-0",
  "score": 77.3,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "xhigh",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2026-02-05",
  "sources": [
   "https://openai.com/index/introducing-gpt-5-3-codex"
  ]
 },
 {
  "model": "openai-gpt-5-4",
  "benchmark": "aa-intelligence-index",
  "score": 57,
  "unit": "index",
  "provenance": "independent",
  "setting": "GPT-5.4 (xhigh); v4.0, stale; superseded by AA v4.3.2",
  "view": "DataLearner mirror of AA Index v4.0",
  "rank": 1,
  "rank_population": null,
  "date": "2026-03-26",
  "sources": [
   "https://www.datalearner.com/en/leaderboards/external/aa-quality-index"
  ],
  "unverified": []
 },
 {
  "model": "openai-gpt-5-5",
  "benchmark": "benchlm-long-context",
  "score": 85.3,
  "unit": "index",
  "provenance": "vendor-reported",
  "setting": "Composite of vendor-reported scores",
  "view": "BenchLM aggregator, top score",
  "rank": 1,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://benchlm.ai/best/long-context"
  ],
  "unverified": []
 },
 {
  "model": "openai-gpt-5-5",
  "benchmark": "financebench",
  "score": 91,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "Aggregator score, not comparable to paper setup; not independently confirmed",
  "view": null,
  "rank": 1,
  "rank_population": null,
  "date": "2026-08-14",
  "sources": [
   "https://capitalandcompute.net/ai-benchmarks/financebench/"
  ]
 },
 {
  "model": "openai-gpt-5-5",
  "benchmark": "swe-bench-pro",
  "score": 58.6,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://rits.shanghai.nyu.edu/ai/openai-releases-gpt-5-5-agentic-coding-ceiling-tops-14-benchmarks/"
  ]
 },
 {
  "model": "openai-gpt-5-5",
  "benchmark": "terminal-bench-2-0",
  "score": 82.7,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://rits.shanghai.nyu.edu/ai/openai-releases-gpt-5-5-agentic-coding-ceiling-tops-14-benchmarks/"
  ]
 },
 {
  "model": "openai-gpt-5-5",
  "benchmark": "terminal-bench-2-0",
  "score": 82,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": "BenchLM aggregator, top score",
  "rank": 1,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://www.benchlm.ai/benchmarks/terminal-bench-2"
  ],
  "unverified": []
 },
 {
  "model": "openai-gpt-5-6-sol",
  "benchmark": "deepswe",
  "score": 73,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://rits.shanghai.nyu.edu/ai/kimi-k3-open-weights-ship-2-8t-parameters-1-4-tb-to-run/"
  ]
 },
 {
  "model": "openai-gpt-5-6-sol",
  "benchmark": "frontiermath",
  "score": 89,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "Legacy aggregate mixing benchmark versions; self-report",
  "view": "BenchLM aggregator, top score",
  "rank": 1,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://www.benchlm.ai/benchmarks/frontiermath"
  ],
  "unverified": []
 },
 {
  "model": "openai-gpt-5-6-sol",
  "benchmark": "gpqa-diamond",
  "score": 94.6,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://docs.apiyi.com/en/news/gpt-6-astra-launch",
   "https://pasqualepillitteri.it/en/news/14246/openai-launches-gpt-6-astra-pricing-benchmarks"
  ]
 },
 {
  "model": "openai-gpt-5-6-sol",
  "benchmark": "lmarena-text",
  "score": 1485,
  "unit": "Elo",
  "provenance": "independent",
  "setting": "xhigh",
  "view": "Arena Text overall",
  "rank": 20,
  "rank_population": null,
  "date": "2026-10-08",
  "sources": [
   "https://arena.ai/leaderboard/chat/text"
  ],
  "uncertainty": "±4"
 },
 {
  "model": "openai-gpt-5-6-sol",
  "benchmark": "swe-bench-pro",
  "score": 64.6,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "public board (per heyuan110)",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://www.heyuan110.com/posts/ai/2026-07-10-gpt-5-6-general-availability/"
  ]
 },
 {
  "model": "openai-gpt-5-6-sol",
  "benchmark": "swe-bench-verified",
  "score": 82.2,
  "unit": "%",
  "provenance": "independent",
  "setting": "max/xhigh, third-party via Thinking Machines",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://leaderboard.steel.dev/leaderboards/swe-bench-verified.md"
  ]
 },
 {
  "model": "openai-gpt-5",
  "benchmark": "healthbench-hard",
  "score": 46.2,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2025-08-07",
  "sources": [
   "https://openai.com/index/introducing-gpt-5/"
  ]
 },
 {
  "model": "openai-gpt-6-1-sol",
  "benchmark": "aa-intelligence-index",
  "score": 52,
  "unit": "index",
  "provenance": "independent",
  "setting": "max",
  "view": "AA leaderboard, 205 current models",
  "rank": 11,
  "rank_population": 205,
  "date": "2026-10-10",
  "sources": [
   "https://artificialanalysis.ai/leaderboards/models"
  ]
 },
 {
  "model": "openai-gpt-6-1-sol",
  "benchmark": "benchlm-composite",
  "score": 81.5,
  "unit": "index",
  "provenance": "vendor-reported",
  "setting": "estimated",
  "view": "benchlm.ai frontier top 6",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-09",
  "sources": [
   "https://benchlm.ai/frontier-ai-models"
  ]
 },
 {
  "model": "openai-gpt-6-1-sol",
  "benchmark": "lmarena-text",
  "score": 1484,
  "unit": "Elo",
  "provenance": "independent",
  "setting": "max",
  "view": "Arena Text overall",
  "rank": 21,
  "rank_population": null,
  "date": "2026-10-08",
  "sources": [
   "https://arena.ai/leaderboard/chat/text"
  ],
  "uncertainty": "±9"
 },
 {
  "model": "openai-gpt-6-1-sol",
  "benchmark": "lmarena-vision",
  "score": 1294,
  "unit": "Elo",
  "provenance": "independent",
  "setting": "max",
  "view": "Arena Vision overall, style control default, 165 models",
  "rank": 8,
  "rank_population": 165,
  "date": "2026-10-09",
  "sources": [
   "https://arena.ai/leaderboard/chat/vision"
  ],
  "uncertainty": "±14"
 },
 {
  "model": "openai-gpt-6-astra",
  "benchmark": "aa-intelligence-index",
  "score": 53,
  "unit": "index",
  "provenance": "independent",
  "setting": "max; 52.67 per secondary",
  "view": "AA leaderboard, 205 current models",
  "rank": 7,
  "rank_population": 205,
  "date": "2026-10-10",
  "sources": [
   "https://artificialanalysis.ai/leaderboards/models"
  ]
 },
 {
  "model": "openai-gpt-6-astra",
  "benchmark": "arc-agi-2",
  "score": 95,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "$1.12/task",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://slash-digital.io/en/insights/ai-models-2026/"
  ]
 },
 {
  "model": "openai-gpt-6-astra",
  "benchmark": "arc-agi-3",
  "score": null,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "direct, about 63 to 66% (apiyi citing Latent Space)",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://docs.apiyi.com/en/news/gpt-6-astra-launch"
  ]
 },
 {
  "model": "openai-gpt-6-astra",
  "benchmark": "arc-agi-3",
  "score": 98.6,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "Conflicting figures across sources",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://pasqualepillitteri.it/en/news/14246/openai-launches-gpt-6-astra-pricing-benchmarks"
  ]
 },
 {
  "model": "openai-gpt-6-astra",
  "benchmark": "arc-agi-3",
  "score": 99.9,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "with OpenAI adapter harness (apiyi citing Latent Space)",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://docs.apiyi.com/en/news/gpt-6-astra-launch"
  ]
 },
 {
  "model": "openai-gpt-6-astra",
  "benchmark": "benchlm-composite",
  "score": 85,
  "unit": "index",
  "provenance": "vendor-reported",
  "setting": null,
  "view": "benchlm.ai frontier top 6",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-09",
  "sources": [
   "https://benchlm.ai/frontier-ai-models"
  ]
 },
 {
  "model": "openai-gpt-6-astra",
  "benchmark": "deepswe-v1-1",
  "score": 74.1,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://pasqualepillitteri.it/en/news/14246/openai-launches-gpt-6-astra-pricing-benchmarks",
   "https://infoq.com/news/2026/09/openai-gpt6-astra"
  ]
 },
 {
  "model": "openai-gpt-6-astra",
  "benchmark": "epoch-capabilities-index",
  "score": 166.41,
  "unit": "index",
  "provenance": "maintainer-run",
  "setting": "Epoch data file of 15 Oct 2026: 0.41 behind Claude Opus 5.5, within each other's confidence intervals",
  "view": "Epoch AI Benchmarking Hub",
  "rank": 2,
  "rank_population": null,
  "date": "2026-10-15",
  "sources": [
   "https://epoch.ai/data/eci_scores.csv",
   "https://epoch.ai/benchmarks"
  ],
  "unverified": [],
  "uncertainty": "CI 163.35 to 171.23"
 },
 {
  "model": "openai-gpt-6-astra",
  "benchmark": "frontiermath-erdos",
  "score": 3,
  "unit": "%",
  "provenance": "maintainer-run",
  "setting": "Solved 2 of 68 problems",
  "view": "Epoch AI Benchmarking Hub",
  "rank": null,
  "rank_population": null,
  "date": "2026-09-03",
  "sources": [
   "https://epoch.ai/benchmarks"
  ],
  "unverified": []
 },
 {
  "model": "openai-gpt-6-astra",
  "benchmark": "frontiermath-tier-4-v2",
  "score": 97.6,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://pasqualepillitteri.it/en/news/14246/openai-launches-gpt-6-astra-pricing-benchmarks"
  ]
 },
 {
  "model": "openai-gpt-6-astra",
  "benchmark": "gpqa-diamond",
  "score": 96,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://docs.apiyi.com/en/news/gpt-6-astra-launch",
   "https://pasqualepillitteri.it/en/news/14246/openai-launches-gpt-6-astra-pricing-benchmarks"
  ]
 },
 {
  "model": "openai-gpt-6-astra",
  "benchmark": "gpqa-diamond",
  "score": 96,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": "BenchLM aggregator, top score",
  "rank": 1,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://www.benchlm.ai/benchmarks/gpqa"
  ],
  "unverified": []
 },
 {
  "model": "openai-gpt-6-astra",
  "benchmark": "lmarena-text",
  "score": 1475,
  "unit": "Elo",
  "provenance": "independent",
  "setting": "max",
  "view": "Arena Text overall",
  "rank": 35,
  "rank_population": null,
  "date": "2026-10-08",
  "sources": [
   "https://arena.ai/leaderboard/chat/text"
  ],
  "uncertainty": "±7"
 },
 {
  "model": "openai-gpt-6-astra",
  "benchmark": "lmarena-vision",
  "score": 1286,
  "unit": "Elo",
  "provenance": "independent",
  "setting": "max",
  "view": "Arena Vision overall, style control default, 165 models",
  "rank": 19,
  "rank_population": 165,
  "date": "2026-10-09",
  "sources": [
   "https://arena.ai/leaderboard/chat/vision"
  ],
  "uncertainty": "±11"
 },
 {
  "model": "openai-gpt-6-astra",
  "benchmark": "openai-mrcr-v2",
  "score": 96.3,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "512K to 1M",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://slash-digital.io/en/insights/ai-models-2026/"
  ]
 },
 {
  "model": "openai-gpt-6-astra",
  "benchmark": "osworld-2-0",
  "score": 72.6,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://pasqualepillitteri.it/en/news/14246/openai-launches-gpt-6-astra-pricing-benchmarks"
  ]
 },
 {
  "model": "openai-gpt-6-astra",
  "benchmark": "terminal-bench-4-0",
  "score": 57.9,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "57.9% to 58.2% across sources",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://vpsranking.com/news/ai/ai-2026-09-22-anthropic-claude-opus-5-5/",
   "https://slash-digital.io/en/insights/ai-models-2026/",
   "https://infoq.com/news/2026/09/openai-gpt6-astra"
  ]
 },
 {
  "model": "openai-gpt-6-luna",
  "benchmark": "aa-intelligence-index",
  "score": 38,
  "unit": "index",
  "provenance": "independent",
  "setting": "max",
  "view": "AA leaderboard, 205 current models",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://artificialanalysis.ai/leaderboards/models"
  ]
 },
 {
  "model": "openai-gpt-image-1-5",
  "benchmark": "aa-image-t2i-v2-0",
  "score": 1107,
  "unit": "Elo",
  "provenance": "independent",
  "setting": "(high); rank shown as 9-14",
  "view": "AA Text-to-Image Arena, overall",
  "rank": 9,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://artificialanalysis.ai/text-to-image/arena/leaderboard-text"
  ]
 },
 {
  "model": "openai-gpt-image-2-5-flare",
  "benchmark": "aa-image-t2i-v2-0",
  "score": 1191,
  "unit": "Elo",
  "provenance": "independent",
  "setting": "(max)",
  "view": "AA Text-to-Image Arena, overall",
  "rank": 2,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://artificialanalysis.ai/text-to-image/arena/leaderboard-text"
  ]
 },
 {
  "model": "openai-gpt-image-2-5-flare",
  "benchmark": "lmarena-text-to-image",
  "score": 1398,
  "unit": "Elo",
  "provenance": "independent",
  "setting": "preliminary",
  "view": "LMArena Text-to-Image, overall, updated 7 Oct 2026",
  "rank": 2,
  "rank_population": null,
  "date": "2026-10-07",
  "sources": [
   "https://arena.ai/leaderboard/text-to-image"
  ],
  "uncertainty": "±7"
 },
 {
  "model": "openai-gpt-image-2-5-sunburst",
  "benchmark": "aa-image-t2i-v2-0",
  "score": 1198,
  "unit": "Elo",
  "provenance": "independent",
  "setting": "(max)",
  "view": "AA Text-to-Image Arena, overall",
  "rank": 1,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://artificialanalysis.ai/text-to-image/arena/leaderboard-text"
  ]
 },
 {
  "model": "openai-gpt-image-2-5-sunburst",
  "benchmark": "lmarena-text-to-image",
  "score": 1425,
  "unit": "Elo",
  "provenance": "independent",
  "setting": "preliminary",
  "view": "LMArena Text-to-Image, overall, updated 7 Oct 2026",
  "rank": 1,
  "rank_population": null,
  "date": "2026-10-07",
  "sources": [
   "https://arena.ai/leaderboard/text-to-image"
  ],
  "uncertainty": "±7"
 },
 {
  "model": "openai-gpt-image-2-5-sunburst",
  "benchmark": "qwen-image-bench",
  "score": 67.01,
  "unit": "score",
  "provenance": "vendor-reported",
  "setting": "Qwen chart only; methodology unreleased",
  "view": "Qwen vendor chart",
  "rank": null,
  "rank_population": null,
  "date": "2026-09",
  "sources": [
   "https://datanorth.ai/news/qwen-releases-qwen-image-2-1"
  ]
 },
 {
  "model": "openai-gpt-image-2",
  "benchmark": "aa-image-t2i-v2-0",
  "score": 1171,
  "unit": "Elo",
  "provenance": "independent",
  "setting": "(high)",
  "view": "AA Text-to-Image Arena, overall",
  "rank": 3,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://artificialanalysis.ai/text-to-image/arena/leaderboard-text"
  ]
 },
 {
  "model": "openai-gpt-image-2",
  "benchmark": "lmarena-text-to-image",
  "score": 1383,
  "unit": "Elo",
  "provenance": "independent",
  "setting": "medium",
  "view": "LMArena Text-to-Image, overall, updated 7 Oct 2026",
  "rank": 3,
  "rank_population": null,
  "date": "2026-10-07",
  "sources": [
   "https://arena.ai/leaderboard/text-to-image"
  ],
  "uncertainty": "±4"
 },
 {
  "model": "openai-gpt-oss-120b",
  "benchmark": "sea-helm",
  "score": 66.14,
  "unit": "score",
  "provenance": "maintainer-run",
  "setting": null,
  "view": "SEA-HELM SEA average, open-weight models",
  "rank": null,
  "rank_population": null,
  "date": "2026-09-18",
  "sources": [
   "https://leaderboard.sea-lion.ai/detailed/SEA"
  ],
  "uncertainty": "95% CI [-0.64, +0.66]"
 },
 {
  "model": "openai-gpt-oss-120b",
  "benchmark": "sea-helm",
  "score": 72.28,
  "unit": "score",
  "provenance": "maintainer-run",
  "setting": null,
  "view": "SEA-HELM Indonesian, open-weight models, average of 2,000 bootstraps",
  "rank": 7,
  "rank_population": null,
  "date": "2026-09-18",
  "sources": [
   "https://leaderboard.sea-lion.ai/detailed/ID"
  ],
  "uncertainty": "95% CI [-1.35, +1.33]"
 },
 {
  "model": "openai-gpt-oss-20b",
  "benchmark": "sea-helm",
  "score": 60.64,
  "unit": "score",
  "provenance": "maintainer-run",
  "setting": "Checkpoint gpt-oss-20b as listed, quantization mxfp4; release view (data last updated 18 Sep 2026); score is the average of 2000 bootstraps",
  "view": "SEA-HELM leaderboard, 58 models, SEA average",
  "rank": null,
  "rank_population": null,
  "date": "2026-09-18",
  "uncertainty": "95% CI [-0.64, +0.63]",
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://leaderboard.sea-lion.ai/detailed/SEA"
  ]
 },
 {
  "model": "openai-gpt-oss-20b",
  "benchmark": "sea-helm",
  "score": 68.38,
  "unit": "score",
  "provenance": "maintainer-run",
  "setting": "Checkpoint gpt-oss-20b as listed, quantization mxfp4; release view (data last updated 18 Sep 2026); score is the average of 2000 bootstraps",
  "view": "SEA-HELM leaderboard, 58 models, Indonesian (ID)",
  "rank": null,
  "rank_population": null,
  "date": "2026-09-18",
  "uncertainty": "95% CI [-1.34, +1.35]",
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://leaderboard.sea-lion.ai/detailed/ID"
  ]
 },
 {
  "model": "openai-sora-2-pro",
  "benchmark": "lmarena-text-to-video",
  "score": 1368,
  "unit": "Elo",
  "provenance": "independent",
  "setting": null,
  "view": "LMArena Text-to-Video, updated 21 Sep 2026",
  "rank": 11,
  "rank_population": null,
  "date": "2026-09-21",
  "sources": [
   "https://arena.ai/leaderboard/text-to-video"
  ],
  "uncertainty": "±7"
 },
 {
  "model": "openai-sora",
  "benchmark": "vbench-2-0",
  "score": 58.38,
  "unit": "%",
  "provenance": "maintainer-run",
  "setting": "Total score; Sora-480p",
  "view": "VBench-2.0",
  "rank": 9,
  "rank_population": null,
  "date": "2025-03-28",
  "sources": [
   "https://huggingface.co/spaces/Vchitect/VBench_Leaderboard"
  ]
 },
 {
  "model": "openai-sora",
  "benchmark": "vbench-2-0",
  "score": 60.57,
  "unit": "%",
  "provenance": "maintainer-run",
  "setting": "Creativity score; Sora-480p",
  "view": "VBench-2.0",
  "rank": null,
  "rank_population": null,
  "date": "2025-03-28",
  "sources": [
   "https://huggingface.co/spaces/Vchitect/VBench_Leaderboard"
  ]
 },
 {
  "model": "openai-whisper-large-v3-turbo",
  "benchmark": "open-asr-leaderboard",
  "score": 7.75,
  "unit": "WER",
  "provenance": "maintainer-run",
  "setting": "average WER per Gladia, from the same leaderboard",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://www.gladia.io/blog/best-open-source-speech-to-text-models"
  ]
 },
 {
  "model": "openai-whisper-large-v3",
  "benchmark": "open-asr-leaderboard",
  "score": 7.4,
  "unit": "WER",
  "provenance": "maintainer-run",
  "setting": "average WER per Gladia, from the same leaderboard",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://www.gladia.io/blog/best-open-source-speech-to-text-models"
  ]
 },
 {
  "model": "openai-whisper-large-v3",
  "benchmark": "open-asr-leaderboard",
  "score": 7.44,
  "unit": "WER",
  "provenance": "maintainer-run",
  "setting": "leadership history",
  "view": "leader in 2023",
  "rank": null,
  "rank_population": null,
  "date": "2023",
  "sources": [
   "https://select.keenable.ai/r/speech-recognition-accuracy-leaders-2022-2026/JbURQjlVooLQ6J10NkbRVw"
  ]
 },
 {
  "model": "openai-whisper-small",
  "benchmark": "idsv",
  "score": 13.84,
  "unit": "CER",
  "provenance": "independent",
  "setting": "IDSV test, all, zero-shot",
  "view": "Table 3",
  "rank": null,
  "rank_population": null,
  "date": "2024-10",
  "sources": [
   "https://arxiv.org/html/2410.08828v2"
  ]
 },
 {
  "model": "openai-whisper-small",
  "benchmark": "idsv",
  "score": 30.87,
  "unit": "WER",
  "provenance": "independent",
  "setting": "IDSV test, all, zero-shot",
  "view": "Table 3",
  "rank": null,
  "rank_population": null,
  "date": "2024-10",
  "sources": [
   "https://arxiv.org/html/2410.08828v2"
  ]
 },
 {
  "model": "openbmb-minicpm-v-4-6-1-3b",
  "benchmark": "aa-intelligence-index",
  "score": 13,
  "unit": "index",
  "provenance": "independent",
  "setting": null,
  "view": "Open models under 2B",
  "rank": 1,
  "rank_population": null,
  "date": "2026-05-11",
  "sources": [
   "https://www.artificialanalysis.ai/articles/openbmb-launches-minicpm-v-4-6-1-3b-instruct"
  ],
  "unverified": []
 },
 {
  "model": "openbmb-minicpm-v-4-6-1-3b",
  "benchmark": "mmmu-pro",
  "score": 38,
  "unit": "%",
  "provenance": "independent",
  "setting": "Reported in Artificial Analysis article; run origin not stated",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2026-05-11",
  "sources": [
   "https://www.artificialanalysis.ai/articles/openbmb-launches-minicpm-v-4-6-1-3b-instruct"
  ],
  "unverified": [
   "provenance"
  ]
 },
 {
  "model": "opendatalab-mineru2-5-pro",
  "benchmark": "omnidocbench-v1-6",
  "score": 95.75,
  "unit": "score",
  "provenance": "vendor-reported",
  "setting": "overall",
  "view": "PaddleOCR-VL-1.6 paper table",
  "rank": null,
  "rank_population": null,
  "date": "2026-06-02",
  "sources": [
   "https://arxiv.org/pdf/2606.03264"
  ]
 },
 {
  "model": "opendatalab-mineru2-5-pro",
  "benchmark": "real5-omnidocbench",
  "score": 88.96,
  "unit": "score",
  "provenance": "vendor-reported",
  "setting": "overall",
  "view": "PaddleOCR-VL-1.6 paper table",
  "rank": null,
  "rank_population": null,
  "date": "2026-06-02",
  "sources": [
   "https://arxiv.org/pdf/2606.03264"
  ]
 },
 {
  "model": "opendatalab-mineru2-5",
  "benchmark": "omnidocbench-v1-6",
  "score": 93.04,
  "unit": "score",
  "provenance": "vendor-reported",
  "setting": "overall",
  "view": "PaddleOCR-VL-1.6 paper table",
  "rank": null,
  "rank_population": null,
  "date": "2026-06-02",
  "sources": [
   "https://arxiv.org/pdf/2606.03264"
  ]
 },
 {
  "model": "opendatalab-mineru2-5",
  "benchmark": "real5-omnidocbench",
  "score": 85.61,
  "unit": "score",
  "provenance": "vendor-reported",
  "setting": "overall",
  "view": "PaddleOCR-VL-1.6 paper table",
  "rank": null,
  "rank_population": null,
  "date": "2026-06-02",
  "sources": [
   "https://arxiv.org/pdf/2606.03264"
  ]
 },
 {
  "model": "orbital-materials-orb-v3",
  "benchmark": "matbench-discovery",
  "score": 0.21,
  "unit": "kSRME",
  "provenance": "maintainer-run",
  "setting": "lower is better",
  "view": "leaderboard fetched 2026-10-10",
  "rank": null,
  "rank_population": null,
  "date": "2025-04-05",
  "sources": [
   "https://matbench-discovery.materialsproject.org/"
  ]
 },
 {
  "model": "orbital-materials-orb-v3",
  "benchmark": "matbench-discovery",
  "score": 0.86,
  "unit": "CPS",
  "provenance": "maintainer-run",
  "setting": null,
  "view": "leaderboard fetched 2026-10-10, ranked by CPS",
  "rank": 10,
  "rank_population": null,
  "date": "2025-04-05",
  "sources": [
   "https://matbench-discovery.materialsproject.org/"
  ]
 },
 {
  "model": "orbital-materials-orb-v3",
  "benchmark": "matbench-discovery",
  "score": 0.905,
  "unit": "F1",
  "provenance": "maintainer-run",
  "setting": null,
  "view": "leaderboard fetched 2026-10-10",
  "rank": null,
  "rank_population": null,
  "date": "2025-04-05",
  "sources": [
   "https://matbench-discovery.materialsproject.org/"
  ]
 },
 {
  "model": "paano",
  "benchmark": "tsb-ad",
  "score": 0.43,
  "unit": "VUS-PR",
  "provenance": "vendor-reported",
  "setting": "Multivariate (TSB-AD-M)",
  "view": null,
  "rank": 1,
  "rank_population": null,
  "date": "2026-07-01",
  "sources": [
   "https://arxiv.org/pdf/2602.01359"
  ]
 },
 {
  "model": "paano",
  "benchmark": "tsb-ad",
  "score": 0.53,
  "unit": "VUS-PR",
  "provenance": "vendor-reported",
  "setting": "Univariate (TSB-AD-U)",
  "view": null,
  "rank": 1,
  "rank_population": null,
  "date": "2026-07-01",
  "sources": [
   "https://arxiv.org/pdf/2602.01359"
  ]
 },
 {
  "model": "paige-virchow",
  "benchmark": "virchow-pan-cancer-detection",
  "score": 0.95,
  "unit": "AUROC",
  "provenance": "vendor-reported",
  "setting": "As reported in the Virchow paper",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2024-07-22",
  "sources": [
   "https://www.nature.com/articles/s41591-024-03141-0"
  ]
 },
 {
  "model": "pca",
  "benchmark": "skab",
  "score": 0.76,
  "unit": "F1",
  "provenance": "maintainer-run",
  "setting": "Outlier detection leaderboard, T-squared+Q (PCA)",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://github.com/waico/SKAB"
  ]
 },
 {
  "model": "pca",
  "benchmark": "tsb-ad",
  "score": 0.31,
  "unit": "VUS-PR",
  "provenance": "independent",
  "setting": "Multivariate; tie with DeepAnT; PaAno paper",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2026-07-01",
  "sources": [
   "https://arxiv.org/pdf/2602.01359"
  ]
 },
 {
  "model": "perpetualbooster",
  "benchmark": "tabarena",
  "score": 1086,
  "unit": "Elo",
  "provenance": "maintainer-run",
  "setting": "best",
  "view": "All Tasks, no imputation, snapshot 2026-05-06, 59 entries",
  "rank": 45,
  "rank_population": 59,
  "date": "2026-05-06",
  "sources": [
   "https://benchmarklist.com/benchmarks/tabarena_all/"
  ]
 },
 {
  "model": "phikon",
  "benchmark": "virchow-pan-cancer-detection",
  "score": 0.932,
  "unit": "AUROC",
  "provenance": "vendor-reported",
  "setting": "As reported in the Virchow paper",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2024-07-22",
  "sources": [
   "https://www.nature.com/articles/s41591-024-03141-0"
  ]
 },
 {
  "model": "pixverse-v6",
  "benchmark": "aa-video-t2v",
  "score": 985,
  "unit": "Elo",
  "provenance": "independent",
  "setting": null,
  "view": "AA Text-to-Video leaderboard",
  "rank": 18,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://artificialanalysis.ai/video/leaderboard/text-to-video"
  ]
 },
 {
  "model": "prior-labs-realtabpfn-2-5",
  "benchmark": "tabarena",
  "score": 1604,
  "unit": "Elo",
  "provenance": "maintainer-run",
  "setting": "tuned + ensembled",
  "view": "All Tasks, no imputation, snapshot 2026-05-06, 59 entries",
  "rank": 3,
  "rank_population": 59,
  "date": "2026-05-06",
  "sources": [
   "https://benchmarklist.com/benchmarks/tabarena_all/",
   "https://benchmarklist.com/benchmarks/tabarena_all/"
  ]
 },
 {
  "model": "prior-labs-tabpfn-2-6",
  "benchmark": "tabarena",
  "score": 1626,
  "unit": "Elo",
  "provenance": "maintainer-run",
  "setting": "default",
  "view": "All Tasks, no imputation, snapshot 2026-05-06, 59 entries",
  "rank": 2,
  "rank_population": 59,
  "date": "2026-05-06",
  "sources": [
   "https://benchmarklist.com/benchmarks/tabarena_all/",
   "https://benchmarklist.com/benchmarks/tabarena_all/"
  ]
 },
 {
  "model": "prior-labs-tabpfn-ts",
  "benchmark": "gift-eval",
  "score": 0.544,
  "unit": "CRPS (geo-mean, normalised to Seasonal Naive)",
  "provenance": "independent",
  "setting": "zero-shot; rank is average CRPS rank",
  "view": "Leaderboard rebuilt from the published raw results, 143 entries covering all 97 configurations",
  "rank": 93,
  "rank_population": 143,
  "date": "2026-10-09",
  "sources": [
   "https://huggingface.co/spaces/Salesforce/GIFT-Eval"
  ],
  "leakage": "no",
  "leakage_note": "Test Leak. column: No (TabPFN-TS (code))"
 },
 {
  "model": "prior-labs-tabpfn-ts",
  "benchmark": "gift-eval",
  "score": 0.771,
  "unit": "MASE (geo-mean, normalised to Seasonal Naive)",
  "provenance": "independent",
  "setting": "zero-shot",
  "view": "Leaderboard rebuilt from the published raw results, 143 entries covering all 97 configurations",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-09",
  "sources": [
   "https://huggingface.co/spaces/Salesforce/GIFT-Eval"
  ],
  "leakage": "no",
  "leakage_note": "Test Leak. column: No (TabPFN-TS (code))"
 },
 {
  "model": "pruna-ai-p-image",
  "benchmark": "aa-image-t2i-v2-0",
  "score": 887,
  "unit": "Elo",
  "provenance": "independent",
  "setting": "Rank range 105 to 114",
  "view": "AA Text-to-Image Arena, 168 models",
  "rank": 110,
  "rank_population": 168,
  "date": "2026-10-11",
  "uncertainty": "880 to 894 (+/-7)",
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://artificialanalysis.ai/image/leaderboard/text-to-image"
  ]
 },
 {
  "model": "pyannoteai-pyannote-community-1",
  "benchmark": "ami",
  "score": 17,
  "unit": "DER %",
  "provenance": "vendor-reported",
  "setting": "AMI IHM, no collar, overlap scored",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2026",
  "sources": [
   "https://www.pyannote.ai/blog/top-7-speaker-diarization-apis-and-models-in-2026"
  ]
 },
 {
  "model": "pyannoteai-pyannote-community-1",
  "benchmark": "ami",
  "score": 19.9,
  "unit": "DER %",
  "provenance": "vendor-reported",
  "setting": "AMI SDM, no collar, overlap scored",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2026",
  "sources": [
   "https://www.pyannote.ai/blog/top-7-speaker-diarization-apis-and-models-in-2026"
  ]
 },
 {
  "model": "pyannoteai-pyannote-community-1",
  "benchmark": "dihard-3",
  "score": 20.2,
  "unit": "DER %",
  "provenance": "vendor-reported",
  "setting": "full, no collar, overlap scored",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2026",
  "sources": [
   "https://www.pyannote.ai/blog/top-7-speaker-diarization-apis-and-models-in-2026"
  ]
 },
 {
  "model": "randomforest",
  "benchmark": "tabarena",
  "score": 1000,
  "unit": "Elo",
  "provenance": "maintainer-run",
  "setting": "default (Elo anchor)",
  "view": "All Tasks, no imputation, snapshot 2026-05-06, 59 entries",
  "rank": null,
  "rank_population": null,
  "date": "2026-05-06",
  "sources": [
   "https://benchmarklist.com/benchmarks/tabarena_all/"
  ]
 },
 {
  "model": "randomforest",
  "benchmark": "tabarena",
  "score": 1172,
  "unit": "Elo",
  "provenance": "maintainer-run",
  "setting": "tuned + ensembled",
  "view": "All Tasks, no imputation, snapshot 2026-05-06, 59 entries",
  "rank": 39,
  "rank_population": 59,
  "date": "2026-05-06",
  "sources": [
   "https://benchmarklist.com/benchmarks/tabarena_all/"
  ]
 },
 {
  "model": "realmlp",
  "benchmark": "tabarena",
  "score": 1514,
  "unit": "Elo",
  "provenance": "maintainer-run",
  "setting": "tuned + ensembled",
  "view": "All Tasks, no imputation, snapshot 2026-05-06, 59 entries",
  "rank": 8,
  "rank_population": 59,
  "date": "2026-05-06",
  "sources": [
   "https://benchmarklist.com/benchmarks/tabarena_all/"
  ]
 },
 {
  "model": "realtime-tts-2",
  "benchmark": "aa-tts",
  "score": 1257,
  "unit": "Elo",
  "provenance": "independent",
  "setting": null,
  "view": "AA Text-to-Speech arena, 96 models",
  "rank": 7,
  "rank_population": 96,
  "date": "2026-10-10",
  "sources": [
   "https://artificialanalysis.ai/text-to-speech/leaderboard"
  ]
 },
 {
  "model": "rednote-dots-ocr",
  "benchmark": "omnidocbench-v1-6",
  "score": 90.77,
  "unit": "score",
  "provenance": "vendor-reported",
  "setting": "overall",
  "view": "PaddleOCR-VL-1.6 paper table",
  "rank": null,
  "rank_population": null,
  "date": "2026-06-02",
  "sources": [
   "https://arxiv.org/pdf/2606.03264"
  ]
 },
 {
  "model": "rednote-dots-ocr",
  "benchmark": "real5-omnidocbench",
  "score": 86.38,
  "unit": "score",
  "provenance": "vendor-reported",
  "setting": "overall",
  "view": "PaddleOCR-VL-1.6 paper table",
  "rank": null,
  "rank_population": null,
  "date": "2026-06-02",
  "sources": [
   "https://arxiv.org/pdf/2606.03264"
  ]
 },
 {
  "model": "reka-ai-reka-flash-3",
  "benchmark": "mmlu-pro",
  "score": 65,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": "Reka Flash 3 announcement",
  "rank": null,
  "rank_population": null,
  "date": "2025-03",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://reka.ai/news/introducing-reka-flash"
  ]
 },
 {
  "model": "reve-2-1",
  "benchmark": "lmarena-text-to-image",
  "score": 1302,
  "unit": "Elo",
  "provenance": "independent",
  "setting": null,
  "view": "LMArena Text-to-Image, overall, updated 7 Oct 2026",
  "rank": 7,
  "rank_population": null,
  "date": "2026-10-07",
  "sources": [
   "https://arena.ai/leaderboard/text-to-image"
  ],
  "uncertainty": "±8"
 },
 {
  "model": "roboflow-rf-detr-2xl",
  "benchmark": "coco",
  "score": 60.1,
  "unit": "AP",
  "provenance": "vendor-reported",
  "setting": "val",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2025-11",
  "sources": [
   "https://arxiv.org/html/2511.09554v2"
  ]
 },
 {
  "model": "roboflow-rf-detr-m",
  "benchmark": "coco",
  "score": 54.7,
  "unit": "AP",
  "provenance": "vendor-reported",
  "setting": "val",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2025-11",
  "sources": [
   "https://arxiv.org/html/2511.09554v2"
  ]
 },
 {
  "model": "roboflow-rf-detr-n",
  "benchmark": "coco",
  "score": 48,
  "unit": "AP",
  "provenance": "vendor-reported",
  "setting": "val",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2025-11",
  "sources": [
   "https://arxiv.org/html/2511.09554v2"
  ]
 },
 {
  "model": "roboflow-rf-detr-s",
  "benchmark": "coco",
  "score": 52.9,
  "unit": "AP",
  "provenance": "vendor-reported",
  "setting": "val",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2025-11",
  "sources": [
   "https://arxiv.org/html/2511.09554v2"
  ]
 },
 {
  "model": "runway-gen-3",
  "benchmark": "worldscore",
  "score": 57.58,
  "unit": "score",
  "provenance": "maintainer-run",
  "setting": "Dynamic aggregate",
  "view": "WorldScore paper table",
  "rank": null,
  "rank_population": null,
  "date": "2025",
  "sources": [
   "https://arxiv.org/html/2504.00983v2"
  ]
 },
 {
  "model": "runway-gen-3",
  "benchmark": "worldscore",
  "score": 60.71,
  "unit": "score",
  "provenance": "maintainer-run",
  "setting": "Static aggregate",
  "view": "WorldScore paper table",
  "rank": null,
  "rank_population": null,
  "date": "2025",
  "sources": [
   "https://arxiv.org/html/2504.00983v2"
  ]
 },
 {
  "model": "salesforce-moirai-2-0-small",
  "benchmark": "gift-eval",
  "score": 0.516,
  "unit": "CRPS (geo-mean, normalised to Seasonal Naive)",
  "provenance": "independent",
  "setting": "pretrained; rank is average CRPS rank",
  "view": "Leaderboard rebuilt from the published raw results, 143 entries covering all 97 configurations",
  "rank": 81,
  "rank_population": 143,
  "date": "2026-10-09",
  "sources": [
   "https://huggingface.co/spaces/Salesforce/GIFT-Eval"
  ],
  "leakage": "no",
  "leakage_note": "Test Leak. column: No (Moirai2 (code))"
 },
 {
  "model": "salesforce-moirai-2-0-small",
  "benchmark": "gift-eval",
  "score": 0.516,
  "unit": "CRPS (normalised)",
  "provenance": "vendor-reported",
  "setting": null,
  "view": "30 foundation models",
  "rank": 6,
  "rank_population": 30,
  "date": "2025-11",
  "sources": [
   "https://arxiv.org/pdf/2511.11698"
  ]
 },
 {
  "model": "salesforce-moirai-2-0-small",
  "benchmark": "gift-eval",
  "score": 0.728,
  "unit": "MASE (geo-mean, normalised to Seasonal Naive)",
  "provenance": "independent",
  "setting": "pretrained",
  "view": "Leaderboard rebuilt from the published raw results, 143 entries covering all 97 configurations",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-09",
  "sources": [
   "https://huggingface.co/spaces/Salesforce/GIFT-Eval"
  ],
  "leakage": "no",
  "leakage_note": "Test Leak. column: No (Moirai2 (code))"
 },
 {
  "model": "salesforce-moirai-2-0-small",
  "benchmark": "gift-eval",
  "score": 0.728,
  "unit": "MASE (normalised)",
  "provenance": "vendor-reported",
  "setting": null,
  "view": "30 foundation models",
  "rank": 5,
  "rank_population": 30,
  "date": "2025-11",
  "sources": [
   "https://arxiv.org/pdf/2511.11698"
  ]
 },
 {
  "model": "salesforce-moirai-2-0-small",
  "benchmark": "gift-eval",
  "score": 36.5,
  "unit": "mean CRPS rank",
  "provenance": "vendor-reported",
  "setting": "zero-shot foundation-model CRPS rank, lower is better",
  "view": "Toto 2.0 report (Datadog)",
  "rank": null,
  "rank_population": null,
  "date": "2026-06",
  "sources": [
   "https://arxiv.org/pdf/2605.20119"
  ]
 },
 {
  "model": "salesforce-moirai-2-0",
  "benchmark": "gift-eval",
  "score": null,
  "unit": null,
  "provenance": "vendor-reported",
  "setting": "arXiv paper ranking among foundation models",
  "view": null,
  "rank": 5,
  "rank_population": 37,
  "date": "2025-11-12",
  "sources": [
   "https://arxiv.org/html/2511.11698v1"
  ]
 },
 {
  "model": "salesforce-moirai-2-0",
  "benchmark": "gift-eval",
  "score": null,
  "unit": "MASE",
  "provenance": "vendor-reported",
  "setting": "Salesforce blog: #1 by MASE among non-leaking FMs",
  "view": null,
  "rank": 1,
  "rank_population": null,
  "date": "2025-08-08",
  "sources": [
   "https://www.salesforce.com/blog/moirai-2-0/"
  ]
 },
 {
  "model": "sand-ai-magi-2-preview",
  "benchmark": "aa-video-t2v",
  "score": 960,
  "unit": "Elo",
  "provenance": "independent",
  "setting": "0912",
  "view": "AA Text-to-Video leaderboard",
  "rank": 21,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://artificialanalysis.ai/video/leaderboard/text-to-video"
  ]
 },
 {
  "model": "sap-rpt-1-oss",
  "benchmark": "tabarena",
  "score": 1284,
  "unit": "Elo",
  "provenance": "maintainer-run",
  "setting": "default",
  "view": "All Tasks, no imputation, snapshot 2026-05-06, 59 entries",
  "rank": 28,
  "rank_population": 59,
  "date": "2026-05-06",
  "sources": [
   "https://benchmarklist.com/benchmarks/tabarena_all/"
  ]
 },
 {
  "model": "sapiens-ai-agnes-video-2-5",
  "benchmark": "aa-video-t2v",
  "score": 1057,
  "unit": "Elo",
  "provenance": "independent",
  "setting": null,
  "view": "AA Text-to-Video leaderboard",
  "rank": 10,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://artificialanalysis.ai/video/leaderboard/text-to-video"
  ]
 },
 {
  "model": "sarvam-ai-sarvam-105b",
  "benchmark": "aa-intelligence-index",
  "score": 9,
  "unit": "index",
  "provenance": "independent",
  "setting": "high; asterisk on page",
  "view": "AA leaderboard, 205 current models",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://artificialanalysis.ai/leaderboards/models"
  ]
 },
 {
  "model": "sarvam-ai-sarvam-105b",
  "benchmark": "gpqa-diamond",
  "score": 78.7,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/sarvamai",
   "https://huggingface.co/sarvamai/sarvam-105b"
  ]
 },
 {
  "model": "sarvam-ai-sarvam-105b",
  "benchmark": "mmlu-pro",
  "score": 81.7,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/sarvamai",
   "https://huggingface.co/sarvamai/sarvam-105b"
  ]
 },
 {
  "model": "sarvam-ai-sarvam-105b",
  "benchmark": "swe-bench-verified",
  "score": 45,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/sarvamai",
   "https://huggingface.co/sarvamai/sarvam-105b"
  ]
 },
 {
  "model": "seasonal-naive",
  "benchmark": "gift-eval",
  "score": 1,
  "unit": "CRPS (geo-mean, normalised to Seasonal Naive)",
  "provenance": "independent",
  "setting": "baseline; rank is average CRPS rank",
  "view": "Leaderboard rebuilt from the published raw results, 143 entries covering all 97 configurations",
  "rank": 138,
  "rank_population": 143,
  "date": "2026-10-09",
  "sources": [
   "https://huggingface.co/spaces/Salesforce/GIFT-Eval"
  ],
  "leakage": "no",
  "leakage_note": "Test Leak. column: No (Seasonal_Naive (code))"
 },
 {
  "model": "seasonal-naive",
  "benchmark": "gift-eval",
  "score": 1,
  "unit": "MASE (geo-mean, normalised to Seasonal Naive)",
  "provenance": "independent",
  "setting": "baseline",
  "view": "Leaderboard rebuilt from the published raw results, 143 entries covering all 97 configurations",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-09",
  "sources": [
   "https://huggingface.co/spaces/Salesforce/GIFT-Eval"
  ]
 },
 {
  "model": "sensenova-u1-a3b-mot",
  "benchmark": "geneval",
  "score": 0.91,
  "unit": "score",
  "provenance": "vendor-reported",
  "setting": "paper-reported, labelled unverified by Codesota; year 2026",
  "view": "Codesota aggregator",
  "rank": 3,
  "rank_population": 7,
  "date": "2026-05-12",
  "sources": [
   "https://arxiv.org/abs/2605.12500",
   "https://www.codesota.com/benchmark/geneval"
  ]
 },
 {
  "model": "seoul-national-university-sevennet-omni-i12",
  "benchmark": "matbench-discovery",
  "score": 0.192,
  "unit": "kSRME",
  "provenance": "maintainer-run",
  "setting": "lower is better",
  "view": "leaderboard fetched 2026-10-10",
  "rank": null,
  "rank_population": null,
  "date": "2026-01-12",
  "sources": [
   "https://matbench-discovery.materialsproject.org/"
  ]
 },
 {
  "model": "seoul-national-university-sevennet-omni-i12",
  "benchmark": "matbench-discovery",
  "score": 0.873,
  "unit": "CPS",
  "provenance": "maintainer-run",
  "setting": null,
  "view": "leaderboard fetched 2026-10-10, ranked by CPS",
  "rank": 6,
  "rank_population": null,
  "date": "2026-01-12",
  "sources": [
   "https://matbench-discovery.materialsproject.org/"
  ]
 },
 {
  "model": "seoul-national-university-sevennet-omni-i12",
  "benchmark": "matbench-discovery",
  "score": 0.906,
  "unit": "F1",
  "provenance": "maintainer-run",
  "setting": null,
  "view": "leaderboard fetched 2026-10-10",
  "rank": null,
  "rank_population": null,
  "date": "2026-01-12",
  "sources": [
   "https://matbench-discovery.materialsproject.org/"
  ]
 },
 {
  "model": "shanghai-ai-laboratory-atria-dawn-preview",
  "benchmark": "browsecomp",
  "score": 92.5,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": "BenchLM aggregator, top score",
  "rank": 1,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://www.benchlm.ai/benchmarks/browsecomp"
  ],
  "unverified": []
 },
 {
  "model": "shengshu-technology-vidu-q1",
  "benchmark": "vbench-2-0",
  "score": 56.54,
  "unit": "%",
  "provenance": "maintainer-run",
  "setting": "Creativity score",
  "view": "VBench-2.0",
  "rank": null,
  "rank_population": null,
  "date": "2025-04-21",
  "sources": [
   "https://huggingface.co/spaces/Vchitect/VBench_Leaderboard"
  ]
 },
 {
  "model": "shengshu-technology-vidu-q1",
  "benchmark": "vbench-2-0",
  "score": 62.7,
  "unit": "%",
  "provenance": "maintainer-run",
  "setting": "Total score",
  "view": "VBench-2.0",
  "rank": 4,
  "rank_population": null,
  "date": "2025-04-21",
  "sources": [
   "https://huggingface.co/spaces/Vchitect/VBench_Leaderboard"
  ]
 },
 {
  "model": "shengshu-technology-vidu-q1",
  "benchmark": "vbench",
  "score": 87.28,
  "unit": "%",
  "provenance": "maintainer-run",
  "setting": "Quality score; submission-based board",
  "view": "VBench (v1) text-to-video",
  "rank": null,
  "rank_population": null,
  "date": "2025-04-21",
  "sources": [
   "https://huggingface.co/spaces/Vchitect/VBench_Leaderboard"
  ]
 },
 {
  "model": "shengshu-technology-vidu-q1",
  "benchmark": "vbench",
  "score": 87.41,
  "unit": "%",
  "provenance": "maintainer-run",
  "setting": "Total score; submission-based board",
  "view": "VBench (v1) text-to-video",
  "rank": 3,
  "rank_population": null,
  "date": "2025-04-21",
  "sources": [
   "https://huggingface.co/spaces/Vchitect/VBench_Leaderboard"
  ]
 },
 {
  "model": "shengshu-technology-vidu-q3-pro",
  "benchmark": "aa-video-i2v-v1-0",
  "score": 1056,
  "unit": "Elo",
  "provenance": "independent",
  "setting": "secondary capture",
  "view": "AA Image-to-Video v1.0",
  "rank": 19,
  "rank_population": null,
  "date": "2026-10",
  "sources": [
   "https://alphasignal.ai/news/shengshu-s-vidu-q4-preview-debuts-at-no-3-for-ai-video"
  ]
 },
 {
  "model": "shengshu-technology-vidu-q3-pro",
  "benchmark": "aa-video-t2v",
  "score": 941,
  "unit": "Elo",
  "provenance": "independent",
  "setting": null,
  "view": "AA Text-to-Video leaderboard",
  "rank": 25,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://artificialanalysis.ai/video/leaderboard/text-to-video"
  ]
 },
 {
  "model": "shengshu-technology-vidu-q4-preview",
  "benchmark": "aa-video-i2v-v1-0",
  "score": 1179,
  "unit": "Elo",
  "provenance": "independent",
  "setting": "secondary capture",
  "view": "AA Image-to-Video v1.0",
  "rank": 3,
  "rank_population": null,
  "date": "2026-10",
  "sources": [
   "https://alphasignal.ai/news/shengshu-s-vidu-q4-preview-debuts-at-no-3-for-ai-video"
  ]
 },
 {
  "model": "simba-3-2",
  "benchmark": "aa-tts",
  "score": 1243,
  "unit": "Elo",
  "provenance": "independent",
  "setting": null,
  "view": "AA Text-to-Speech arena, 96 models",
  "rank": 9,
  "rank_population": 96,
  "date": "2026-10-10",
  "sources": [
   "https://artificialanalysis.ai/text-to-speech/leaderboard"
  ]
 },
 {
  "model": "sk-telecom-a-x-k2",
  "benchmark": "aa-lcr-v1-1",
  "score": 66,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "Thinking mode; AA-LCR",
  "view": "A.X K2 model card",
  "rank": null,
  "rank_population": null,
  "date": "2026-07",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://huggingface.co/skt/A.X-K2"
  ]
 },
 {
  "model": "sk-telecom-a-x-k2",
  "benchmark": "browsecomp",
  "score": 9.3,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "Thinking mode; At most 10 searches",
  "view": "A.X K2 model card",
  "rank": null,
  "rank_population": null,
  "date": "2026-07",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://huggingface.co/skt/A.X-K2"
  ]
 },
 {
  "model": "sk-telecom-a-x-k2",
  "benchmark": "gpqa-diamond",
  "score": 85.6,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "Thinking mode",
  "view": "A.X K2 model card",
  "rank": null,
  "rank_population": null,
  "date": "2026-07",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://huggingface.co/skt/A.X-K2"
  ]
 },
 {
  "model": "sk-telecom-a-x-k2",
  "benchmark": "hle",
  "score": 27.8,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "Thinking mode",
  "view": "A.X K2 model card",
  "rank": null,
  "rank_population": null,
  "date": "2026-07",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://huggingface.co/skt/A.X-K2"
  ]
 },
 {
  "model": "sk-telecom-a-x-k2",
  "benchmark": "ifbench",
  "score": 75.9,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "Thinking mode",
  "view": "A.X K2 model card",
  "rank": null,
  "rank_population": null,
  "date": "2026-07",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://huggingface.co/skt/A.X-K2"
  ]
 },
 {
  "model": "sk-telecom-a-x-k2",
  "benchmark": "kmmlu-pro",
  "score": 80.5,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "Thinking mode",
  "view": "A.X K2 model card",
  "rank": null,
  "rank_population": null,
  "date": "2026-07",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://huggingface.co/skt/A.X-K2"
  ]
 },
 {
  "model": "sk-telecom-a-x-k2",
  "benchmark": "livecodebench-v6",
  "score": 84,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "Thinking mode; Feb to May window",
  "view": "A.X K2 model card",
  "rank": null,
  "rank_population": null,
  "date": "2026-07",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://huggingface.co/skt/A.X-K2"
  ]
 },
 {
  "model": "sk-telecom-a-x-k2",
  "benchmark": "ruler",
  "score": 94.6,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "Thinking mode; Overall average",
  "view": "A.X K2 model card",
  "rank": null,
  "rank_population": null,
  "date": "2026-07",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://huggingface.co/skt/A.X-K2"
  ]
 },
 {
  "model": "sk-telecom-a-x-k2",
  "benchmark": "scicode",
  "score": 41,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "Thinking mode",
  "view": "A.X K2 model card",
  "rank": null,
  "rank_population": null,
  "date": "2026-07",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://huggingface.co/skt/A.X-K2"
  ]
 },
 {
  "model": "sk-telecom-a-x-k2",
  "benchmark": "tau2-bench",
  "score": 98,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "Thinking mode; Telecom",
  "view": "A.X K2 model card",
  "rank": null,
  "rank_population": null,
  "date": "2026-07",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://huggingface.co/skt/A.X-K2"
  ]
 },
 {
  "model": "sk-telecom-a-x-k2",
  "benchmark": "terminal-bench-2-1",
  "score": 36,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "Thinking mode",
  "view": "A.X K2 model card",
  "rank": null,
  "rank_population": null,
  "date": "2026-07",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://huggingface.co/skt/A.X-K2"
  ]
 },
 {
  "model": "skywork-ai-skyreels-v4",
  "benchmark": "aa-video-t2v",
  "score": 1074,
  "unit": "Elo",
  "provenance": "independent",
  "setting": null,
  "view": "AA Text-to-Video leaderboard",
  "rank": 9,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://artificialanalysis.ai/video/leaderboard/text-to-video"
  ]
 },
 {
  "model": "spacexai-grok-4-20",
  "benchmark": "lmarena-text",
  "score": 1475,
  "unit": "Elo",
  "provenance": "independent",
  "setting": "grok-4.20-beta1",
  "view": "Arena Text overall",
  "rank": 37,
  "rank_population": null,
  "date": "2026-10-08",
  "sources": [
   "https://arena.ai/leaderboard/chat/text"
  ],
  "uncertainty": "±5"
 },
 {
  "model": "spacexai-grok-4-7",
  "benchmark": "aa-intelligence-index",
  "score": 46,
  "unit": "index",
  "provenance": "independent",
  "setting": "xhigh",
  "view": "AA leaderboard, 205 current models",
  "rank": 23,
  "rank_population": 205,
  "date": "2026-10-10",
  "sources": [
   "https://artificialanalysis.ai/leaderboards/models"
  ]
 },
 {
  "model": "spacexai-grok-4-7",
  "benchmark": "aa-intelligence-index",
  "score": 46,
  "unit": "index",
  "provenance": "independent",
  "setting": "xhigh",
  "view": "AA model page, 227 models",
  "rank": 29,
  "rank_population": 227,
  "date": "2026-10-10",
  "sources": [
   "https://artificialanalysis.ai/models/grok-4-7"
  ]
 },
 {
  "model": "spacexai-grok-4-7",
  "benchmark": "terminal-bench-4-0",
  "score": 37.6,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": 10,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://slash-digital.io/en/insights/ai-models-2026/"
  ]
 },
 {
  "model": "spacexai-grok-code-fast-1",
  "benchmark": "swe-bench-verified",
  "score": 70.8,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "xAI internal harness",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://www.verdent.ai/guides/grok-for-coding-2026"
  ]
 },
 {
  "model": "spacexai-grok-imagine-image-2-0",
  "benchmark": "aa-image-t2i-v2-0",
  "score": 1156,
  "unit": "Elo",
  "provenance": "independent",
  "setting": "rank shown as 4-6",
  "view": "AA Text-to-Image Arena, overall",
  "rank": 4,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://artificialanalysis.ai/text-to-image/arena/leaderboard-text"
  ]
 },
 {
  "model": "spacexai-grok-imagine-image-2-0",
  "benchmark": "lmarena-text-to-image",
  "score": 1334,
  "unit": "Elo",
  "provenance": "independent",
  "setting": "canvas; preliminary",
  "view": "LMArena Text-to-Image, overall, updated 7 Oct 2026",
  "rank": 4,
  "rank_population": null,
  "date": "2026-10-07",
  "sources": [
   "https://arena.ai/leaderboard/text-to-image"
  ],
  "uncertainty": "±12"
 },
 {
  "model": "spacexai-grok-imagine-video-1-5",
  "benchmark": "aa-video-t2v",
  "score": 1045,
  "unit": "Elo",
  "provenance": "independent",
  "setting": null,
  "view": "AA Text-to-Video leaderboard",
  "rank": 11,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://artificialanalysis.ai/video/leaderboard/text-to-video"
  ]
 },
 {
  "model": "spacexai-grok-imagine-video-1-5",
  "benchmark": "lmarena-text-to-video",
  "score": 1492,
  "unit": "Elo",
  "provenance": "independent",
  "setting": "agent; preliminary",
  "view": "LMArena Text-to-Video, updated 21 Sep 2026",
  "rank": 4,
  "rank_population": null,
  "date": "2026-09-21",
  "sources": [
   "https://arena.ai/leaderboard/text-to-video"
  ],
  "uncertainty": "±18"
 },
 {
  "model": "spacexai-tts",
  "benchmark": "aa-tts",
  "score": 1143,
  "unit": "Elo",
  "provenance": "independent",
  "setting": null,
  "view": "AA Text-to-Speech arena, 96 models",
  "rank": 25,
  "rank_population": 96,
  "date": "2026-10-10",
  "sources": [
   "https://artificialanalysis.ai/text-to-speech/leaderboard"
  ]
 },
 {
  "model": "spark-4-0-2024-10-14",
  "benchmark": "cmmlu",
  "score": 90.97,
  "unit": "%",
  "provenance": "maintainer-run",
  "setting": "Zero-shot",
  "view": "CMMLU leaderboard",
  "rank": 1,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://github.com/haonan-li/CMMLU"
  ],
  "unverified": []
 },
 {
  "model": "speechbrain-ecapa-tdnn",
  "benchmark": "voxceleb1",
  "score": 0.8,
  "unit": "EER %",
  "provenance": "vendor-reported",
  "setting": "cleaned VoxCeleb1, speaker verification",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://www.pyannote.ai/blog/top-7-speaker-diarization-apis-and-models-in-2026"
  ]
 },
 {
  "model": "stability-ai-stable-audio-3-medium",
  "benchmark": "aa-music-arena-v1-1",
  "score": 998,
  "unit": "Elo",
  "provenance": "independent",
  "setting": "secondary capture of AA post",
  "view": "AA Music Arena v1.1, Instrumental",
  "rank": null,
  "rank_population": null,
  "date": "2026-10",
  "sources": [
   "https://alphasignal.ai/news/artificial-analysis-music-arena-v1-1-crowns-suno-v6-across-1-000-harder-prompts",
   "https://digg.com/ai/g8egglmo"
  ]
 },
 {
  "model": "stanford-university-openvla-oft",
  "benchmark": "libero",
  "score": 97.1,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "Average",
  "view": "OpenVLA-OFT paper",
  "rank": null,
  "rank_population": null,
  "date": "2025-02",
  "sources": [
   "https://arxiv.org/abs/2502.19645"
  ]
 },
 {
  "model": "stanford-university-openvla",
  "benchmark": "libero",
  "score": 76.5,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "Average; baseline reported in OpenVLA-OFT paper",
  "view": "OpenVLA-OFT paper",
  "rank": null,
  "rank_population": null,
  "date": "2025-02",
  "sources": [
   "https://arxiv.org/abs/2502.19645"
  ]
 },
 {
  "model": "stanford-university-s1",
  "benchmark": "aime-2024",
  "score": 56.7,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "after SFT on 1,000 examples (base 26.7)",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2025-01",
  "sources": [
   "https://arxiv.org/html/2501.19393v1"
  ]
 },
 {
  "model": "stepaudio-2-5-tts",
  "benchmark": "aa-tts",
  "score": 1209,
  "unit": "Elo",
  "provenance": "independent",
  "setting": null,
  "view": "AA Text-to-Speech arena, 96 models",
  "rank": 14,
  "rank_population": 96,
  "date": "2026-10-10",
  "sources": [
   "https://artificialanalysis.ai/text-to-speech/leaderboard"
  ]
 },
 {
  "model": "stepfun-step-3-7-flash",
  "benchmark": "hle",
  "score": 48.1,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "with tools",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/stepfun-ai/Step-3.7-Flash"
  ]
 },
 {
  "model": "stepfun-step-3-7-flash",
  "benchmark": "swe-bench-pro",
  "score": 56.3,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/stepfun-ai/Step-3.7-Flash"
  ]
 },
 {
  "model": "stepfun-step-5-preview",
  "benchmark": "aa-intelligence-index",
  "score": 44,
  "unit": "index",
  "provenance": "independent",
  "setting": null,
  "view": "AA leaderboard, 205 current models",
  "rank": 30,
  "rank_population": 205,
  "date": "2026-10-10",
  "sources": [
   "https://artificialanalysis.ai/leaderboards/models"
  ]
 },
 {
  "model": "stepfun-step-5-preview",
  "benchmark": "lmarena-text",
  "score": null,
  "unit": "Elo",
  "provenance": "independent",
  "setting": null,
  "view": "Arena Text overall",
  "rank": 83,
  "rank_population": null,
  "date": "2026-10-08",
  "sources": [
   "https://arena.ai/leaderboard/chat/text"
  ]
 },
 {
  "model": "stormer",
  "benchmark": "weatherbench-2",
  "score": 134.4,
  "unit": "RMSE m2/s2",
  "provenance": "maintainer-run",
  "setting": "Z500 day 3, deterministic, Stormer ENS (mean) vs ERA5",
  "view": "year 2020, 240x121 grid",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://researchsites.withgoogle.com/weatherbench/deterministic/"
  ]
 },
 {
  "model": "stormer",
  "benchmark": "weatherbench-2",
  "score": 285.9,
  "unit": "RMSE m2/s2",
  "provenance": "maintainer-run",
  "setting": "Z500 day 5, deterministic, Stormer ENS (mean) vs ERA5",
  "view": "year 2020, 240x121 grid",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://researchsites.withgoogle.com/weatherbench/deterministic/"
  ]
 },
 {
  "model": "stormer",
  "benchmark": "weatherbench-2",
  "score": 45.2,
  "unit": "RMSE m2/s2",
  "provenance": "maintainer-run",
  "setting": "Z500 day 1, deterministic, Stormer ENS (mean) vs ERA5",
  "view": "year 2020, 240x121 grid",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://researchsites.withgoogle.com/weatherbench/deterministic/"
  ]
 },
 {
  "model": "stormer",
  "benchmark": "weatherbench-2",
  "score": 665.9,
  "unit": "RMSE m2/s2",
  "provenance": "maintainer-run",
  "setting": "Z500 day 10, deterministic, Stormer ENS (mean) vs ERA5",
  "view": "year 2020, 240x121 grid",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://researchsites.withgoogle.com/weatherbench/deterministic/"
  ]
 },
 {
  "model": "sub-pca",
  "benchmark": "tsb-ad",
  "score": 0.42,
  "unit": "VUS-PR",
  "provenance": "independent",
  "setting": "Univariate; as reported in the PaAno paper",
  "view": null,
  "rank": 2,
  "rank_population": null,
  "date": "2026-07-01",
  "sources": [
   "https://arxiv.org/pdf/2602.01359"
  ]
 },
 {
  "model": "suno-v6-mini",
  "benchmark": "aa-music-arena-v1-1",
  "score": 1109,
  "unit": "Elo",
  "provenance": "independent",
  "setting": "secondary capture of AA post",
  "view": "AA Music Arena v1.1, Instrumental",
  "rank": 2,
  "rank_population": null,
  "date": "2026-10",
  "sources": [
   "https://alphasignal.ai/news/artificial-analysis-music-arena-v1-1-crowns-suno-v6-across-1-000-harder-prompts",
   "https://digg.com/ai/g8egglmo"
  ]
 },
 {
  "model": "suno-v6-mini",
  "benchmark": "aa-music-arena-v1-1",
  "score": 1116,
  "unit": "Elo",
  "provenance": "independent",
  "setting": "secondary capture of AA post",
  "view": "AA Music Arena v1.1, Vocal",
  "rank": 2,
  "rank_population": null,
  "date": "2026-10",
  "sources": [
   "https://alphasignal.ai/news/artificial-analysis-music-arena-v1-1-crowns-suno-v6-across-1-000-harder-prompts",
   "https://digg.com/ai/g8egglmo"
  ]
 },
 {
  "model": "suno-v6",
  "benchmark": "aa-music-arena-v1-1",
  "score": 1140,
  "unit": "Elo",
  "provenance": "independent",
  "setting": "secondary capture of AA post",
  "view": "AA Music Arena v1.1, Instrumental",
  "rank": 1,
  "rank_population": null,
  "date": "2026-10",
  "sources": [
   "https://alphasignal.ai/news/artificial-analysis-music-arena-v1-1-crowns-suno-v6-across-1-000-harder-prompts",
   "https://digg.com/ai/g8egglmo"
  ]
 },
 {
  "model": "suno-v6",
  "benchmark": "aa-music-arena-v1-1",
  "score": 1142,
  "unit": "Elo",
  "provenance": "independent",
  "setting": "secondary capture of AA post",
  "view": "AA Music Arena v1.1, Vocal",
  "rank": 1,
  "rank_population": null,
  "date": "2026-10",
  "sources": [
   "https://alphasignal.ai/news/artificial-analysis-music-arena-v1-1-crowns-suno-v6-across-1-000-harder-prompts",
   "https://digg.com/ai/g8egglmo"
  ]
 },
 {
  "model": "swiss-ai-apertus-v1-5-70b",
  "benchmark": "sea-helm",
  "score": 55.2,
  "unit": "score",
  "provenance": "maintainer-run",
  "setting": null,
  "view": "SEA-HELM SEA average, open-weight models",
  "rank": null,
  "rank_population": null,
  "date": "2026-09-18",
  "sources": [
   "https://leaderboard.sea-lion.ai/detailed/SEA"
  ],
  "uncertainty": "95% CI [-0.66, +0.61]"
 },
 {
  "model": "swiss-ai-apertus-v1-5-70b",
  "benchmark": "sea-helm",
  "score": 64.69,
  "unit": "score",
  "provenance": "maintainer-run",
  "setting": null,
  "view": "SEA-HELM Indonesian, open-weight models, average of 2,000 bootstraps",
  "rank": null,
  "rank_population": null,
  "date": "2026-09-18",
  "sources": [
   "https://leaderboard.sea-lion.ai/detailed/ID"
  ],
  "uncertainty": "95% CI [-1.37, +1.36]"
 },
 {
  "model": "swiss-ai-apertus-v1-5-8b",
  "benchmark": "sea-helm",
  "score": 54.16,
  "unit": "score",
  "provenance": "maintainer-run",
  "setting": "Checkpoint Apertus-v1.5-8B as listed; release view (data last updated 18 Sep 2026); score is the average of 2000 bootstraps",
  "view": "SEA-HELM leaderboard, 58 models, SEA average",
  "rank": null,
  "rank_population": null,
  "date": "2026-09-18",
  "uncertainty": "95% CI [-0.62, +0.62]",
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://leaderboard.sea-lion.ai/detailed/SEA"
  ]
 },
 {
  "model": "swiss-ai-apertus-v1-5-8b",
  "benchmark": "sea-helm",
  "score": 62.23,
  "unit": "score",
  "provenance": "maintainer-run",
  "setting": "Checkpoint Apertus-v1.5-8B as listed; release view (data last updated 18 Sep 2026); score is the average of 2000 bootstraps",
  "view": "SEA-HELM leaderboard, 58 models, Indonesian (ID)",
  "rank": null,
  "rank_population": null,
  "date": "2026-09-18",
  "uncertainty": "95% CI [-1.32, +1.32]",
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://leaderboard.sea-lion.ai/detailed/ID"
  ]
 },
 {
  "model": "tabm",
  "benchmark": "tabarena",
  "score": 1448,
  "unit": "Elo",
  "provenance": "maintainer-run",
  "setting": "tuned + ensembled",
  "view": "All Tasks, no imputation, snapshot 2026-05-06, 59 entries",
  "rank": 10,
  "rank_population": 59,
  "date": "2026-05-06",
  "sources": [
   "https://benchmarklist.com/benchmarks/tabarena_all/"
  ]
 },
 {
  "model": "tace-v1-oam-m",
  "benchmark": "matbench-discovery",
  "score": 0.173,
  "unit": "kSRME",
  "provenance": "maintainer-run",
  "setting": "lower is better",
  "view": "leaderboard fetched 2026-10-10",
  "rank": null,
  "rank_population": null,
  "date": "2026-01-06",
  "sources": [
   "https://matbench-discovery.materialsproject.org/"
  ]
 },
 {
  "model": "tace-v1-oam-m",
  "benchmark": "matbench-discovery",
  "score": 0.867,
  "unit": "CPS",
  "provenance": "maintainer-run",
  "setting": null,
  "view": "leaderboard fetched 2026-10-10, ranked by CPS",
  "rank": 8,
  "rank_population": null,
  "date": "2026-01-06",
  "sources": [
   "https://matbench-discovery.materialsproject.org/"
  ]
 },
 {
  "model": "tace-v1-oam-m",
  "benchmark": "matbench-discovery",
  "score": 0.889,
  "unit": "F1",
  "provenance": "maintainer-run",
  "setting": null,
  "view": "leaderboard fetched 2026-10-10",
  "rank": null,
  "rank_population": null,
  "date": "2026-01-06",
  "sources": [
   "https://matbench-discovery.materialsproject.org/"
  ]
 },
 {
  "model": "tencent-hunyuanimage-3-0-instruct",
  "benchmark": "aa-image-t2i-v2-0",
  "score": 996,
  "unit": "Elo",
  "provenance": "independent",
  "setting": "approximate rank",
  "view": "AA Text-to-Image Arena, overall",
  "rank": 50,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://artificialanalysis.ai/text-to-image/arena/leaderboard-text"
  ]
 },
 {
  "model": "tencent-hunyuanimage-3-0",
  "benchmark": "aa-image-t2i-v2-0",
  "score": 945,
  "unit": "Elo",
  "provenance": "independent",
  "setting": "approximate rank",
  "view": "AA Text-to-Image Arena, overall",
  "rank": 80,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://artificialanalysis.ai/text-to-image/arena/leaderboard-text"
  ]
 },
 {
  "model": "tencent-hunyuanimage-3-5-preview",
  "benchmark": "aa-image-t2i-v2-0",
  "score": 976,
  "unit": "Elo",
  "provenance": "independent",
  "setting": null,
  "view": "AA Text-to-Image Arena, overall",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://artificialanalysis.ai/text-to-image/arena/leaderboard-text"
  ]
 },
 {
  "model": "tencent-hy3",
  "benchmark": "aa-intelligence-index",
  "score": 25,
  "unit": "index",
  "provenance": "independent",
  "setting": null,
  "view": "AA leaderboard, 205 current models",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://artificialanalysis.ai/leaderboards/models"
  ]
 },
 {
  "model": "tencent-hy3",
  "benchmark": "gpqa-diamond",
  "score": 90.4,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/tencent/Hy3"
  ]
 },
 {
  "model": "tencent-hy3",
  "benchmark": "lmarena-text",
  "score": null,
  "unit": "Elo",
  "provenance": "independent",
  "setting": null,
  "view": "Arena Text overall",
  "rank": 73,
  "rank_population": null,
  "date": "2026-10-08",
  "sources": [
   "https://arena.ai/leaderboard/chat/text"
  ]
 },
 {
  "model": "tencent-hy3",
  "benchmark": "swe-bench-verified",
  "score": 78,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/tencent/Hy3"
  ]
 },
 {
  "model": "tencent-hy4-preview",
  "benchmark": "gpqa-diamond",
  "score": 92.3,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/tencent/Hy4-preview"
  ]
 },
 {
  "model": "tencent-hy4-preview",
  "benchmark": "swe-bench-pro",
  "score": 65.7,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/tencent/Hy4-preview"
  ]
 },
 {
  "model": "tencent-hy4-preview",
  "benchmark": "terminal-bench-2-1",
  "score": 85.4,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/tencent/Hy4-preview"
  ]
 },
 {
  "model": "thinking-machines-inkling",
  "benchmark": "swe-bench-verified",
  "score": 77.6,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "effort 0.99",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://leaderboard.steel.dev/leaderboards/swe-bench-verified.md"
  ]
 },
 {
  "model": "tianji",
  "benchmark": "weatherbench-2",
  "score": 1.424,
  "unit": "RMSE K",
  "provenance": "maintainer-run",
  "setting": "T850 day 5, deterministic, Tianji vs ERA5",
  "view": "year 2022, 240x121 grid",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://researchsites.withgoogle.com/weatherbench/deterministic/"
  ]
 },
 {
  "model": "tianji",
  "benchmark": "weatherbench-2",
  "score": 112.4,
  "unit": "RMSE m2/s2",
  "provenance": "maintainer-run",
  "setting": "Z500 day 3, deterministic, Tianji vs ERA5",
  "view": "year 2022, 240x121 grid",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://researchsites.withgoogle.com/weatherbench/deterministic/"
  ]
 },
 {
  "model": "tianji",
  "benchmark": "weatherbench-2",
  "score": 2.674,
  "unit": "RMSE K",
  "provenance": "maintainer-run",
  "setting": "T850 day 10, deterministic, Tianji vs ERA5",
  "view": "year 2022, 240x121 grid",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://researchsites.withgoogle.com/weatherbench/deterministic/"
  ]
 },
 {
  "model": "tianji",
  "benchmark": "weatherbench-2",
  "score": 250.3,
  "unit": "RMSE m2/s2",
  "provenance": "maintainer-run",
  "setting": "Z500 day 5, deterministic, Tianji vs ERA5",
  "view": "year 2022, 240x121 grid",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://researchsites.withgoogle.com/weatherbench/deterministic/"
  ]
 },
 {
  "model": "tianji",
  "benchmark": "weatherbench-2",
  "score": 33.3,
  "unit": "RMSE m2/s2",
  "provenance": "maintainer-run",
  "setting": "Z500 day 1, deterministic, Tianji vs ERA5",
  "view": "year 2022, 240x121 grid",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://researchsites.withgoogle.com/weatherbench/deterministic/"
  ]
 },
 {
  "model": "tianji",
  "benchmark": "weatherbench-2",
  "score": 599.4,
  "unit": "RMSE m2/s2",
  "provenance": "maintainer-run",
  "setting": "Z500 day 10, deterministic, Tianji vs ERA5",
  "view": "year 2022, 240x121 grid",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://researchsites.withgoogle.com/weatherbench/deterministic/"
  ]
 },
 {
  "model": "tii-falcon-h1r-7b",
  "benchmark": "aime-2025",
  "score": 83.1,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/tiiuae/Falcon-H1R-7B"
  ]
 },
 {
  "model": "tii-falcon-h1r-7b",
  "benchmark": "math-500",
  "score": 97.4,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/tiiuae/Falcon-H1R-7B"
  ]
 },
 {
  "model": "tomoviee-2-0",
  "benchmark": "vbench-2-0",
  "score": 45.96,
  "unit": "%",
  "provenance": "maintainer-run",
  "setting": "Creativity score",
  "view": "VBench-2.0",
  "rank": null,
  "rank_population": null,
  "date": "2025-09-18",
  "sources": [
   "https://huggingface.co/spaces/Vchitect/VBench_Leaderboard"
  ]
 },
 {
  "model": "tomoviee-2-0",
  "benchmark": "vbench-2-0",
  "score": 61.78,
  "unit": "%",
  "provenance": "maintainer-run",
  "setting": "Total score",
  "view": "VBench-2.0",
  "rank": 5,
  "rank_population": null,
  "date": "2025-09-18",
  "sources": [
   "https://huggingface.co/spaces/Vchitect/VBench_Leaderboard"
  ]
 },
 {
  "model": "tsinghua-university-dinomaly2",
  "benchmark": "mvtec-ad",
  "score": 99.9,
  "unit": "AUROC",
  "provenance": "vendor-reported",
  "setting": "Dinomaly2-L, multi-class unified, image AUROC",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2025-10-24",
  "sources": [
   "https://arxiv.org/pdf/2510.17611"
  ]
 },
 {
  "model": "tsinghua-university-dinomaly2",
  "benchmark": "real-iad",
  "score": 92.1,
  "unit": "AUROC",
  "provenance": "vendor-reported",
  "setting": "Dinomaly2-L, multi-class unified, image AUROC",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2025-10-24",
  "sources": [
   "https://arxiv.org/pdf/2510.17611"
  ]
 },
 {
  "model": "tsinghua-university-dinomaly2",
  "benchmark": "visa",
  "score": 99.3,
  "unit": "AUROC",
  "provenance": "vendor-reported",
  "setting": "Dinomaly2-L, multi-class unified, image AUROC",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2025-10-24",
  "sources": [
   "https://arxiv.org/pdf/2510.17611"
  ]
 },
 {
  "model": "tsinghua-university-sundial-base-128m",
  "benchmark": "gift-eval",
  "score": null,
  "unit": "MASE rank",
  "provenance": "vendor-reported",
  "setting": "MASE",
  "view": null,
  "rank": 1,
  "rank_population": null,
  "date": "2025-05",
  "sources": [
   "https://huggingface.co/thuml/sundial-base-128m"
  ]
 },
 {
  "model": "tsinghua-university-sundial-base-128m",
  "benchmark": "gift-eval",
  "score": 0.559,
  "unit": "CRPS (geo-mean, normalised to Seasonal Naive)",
  "provenance": "independent",
  "setting": "zero-shot; rank is average CRPS rank",
  "view": "Leaderboard rebuilt from the published raw results, 143 entries covering all 97 configurations",
  "rank": 106,
  "rank_population": 143,
  "date": "2026-10-09",
  "sources": [
   "https://huggingface.co/spaces/Salesforce/GIFT-Eval"
  ],
  "leakage": "no",
  "leakage_note": "Test Leak. column: No (sundial_base_128m (code))"
 },
 {
  "model": "tsinghua-university-sundial-base-128m",
  "benchmark": "gift-eval",
  "score": 0.75,
  "unit": "MASE (geo-mean, normalised to Seasonal Naive)",
  "provenance": "independent",
  "setting": "zero-shot",
  "view": "Leaderboard rebuilt from the published raw results, 143 entries covering all 97 configurations",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-09",
  "sources": [
   "https://huggingface.co/spaces/Salesforce/GIFT-Eval"
  ],
  "leakage": "no",
  "leakage_note": "Test Leak. column: No (sundial_base_128m (code))"
 },
 {
  "model": "tsinghua-university-timer-s1",
  "benchmark": "gift-eval",
  "score": 0.485,
  "unit": "CRPS (geo-mean, normalised to Seasonal Naive)",
  "provenance": "independent",
  "setting": "pretrained; rank is average CRPS rank",
  "view": "Leaderboard rebuilt from the published raw results, 143 entries covering all 97 configurations",
  "rank": 68,
  "rank_population": 143,
  "date": "2026-10-09",
  "sources": [
   "https://huggingface.co/spaces/Salesforce/GIFT-Eval"
  ],
  "leakage": "no",
  "leakage_note": "Test Leak. column: No (Timer-S1 (code))"
 },
 {
  "model": "tsinghua-university-timer-s1",
  "benchmark": "gift-eval",
  "score": 0.693,
  "unit": "MASE (geo-mean, normalised to Seasonal Naive)",
  "provenance": "independent",
  "setting": "pretrained",
  "view": "Leaderboard rebuilt from the published raw results, 143 entries covering all 97 configurations",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-09",
  "sources": [
   "https://huggingface.co/spaces/Salesforce/GIFT-Eval"
  ],
  "leakage": "no",
  "leakage_note": "Test Leak. column: No (Timer-S1 (code))"
 },
 {
  "model": "tsinghua-university-timer-s1",
  "benchmark": "gift-eval",
  "score": 26.5,
  "unit": "mean CRPS rank",
  "provenance": "vendor-reported",
  "setting": "zero-shot foundation-model CRPS rank, lower is better",
  "view": "Toto 2.0 report (Datadog)",
  "rank": null,
  "rank_population": null,
  "date": "2026-06",
  "sources": [
   "https://arxiv.org/pdf/2605.20119"
  ]
 },
 {
  "model": "tsinghua-university-video-salmonn-2-plus-72b",
  "benchmark": "video-mme",
  "score": 81.6,
  "unit": "%",
  "provenance": "maintainer-run",
  "setting": "With subtitles",
  "view": "Video-MME leaderboard",
  "rank": 1,
  "rank_population": null,
  "date": "2025-09-28",
  "sources": [
   "https://video-mme.github.io/home_page.html"
  ],
  "unverified": []
 },
 {
  "model": "ultralytics-yolo11",
  "benchmark": "coco",
  "score": 37.1,
  "unit": "AP",
  "provenance": "independent",
  "setting": "val, N size, as reported in RF-DETR paper",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2025-11",
  "sources": [
   "https://arxiv.org/html/2511.09554v2"
  ]
 },
 {
  "model": "ultralytics-yolo11",
  "benchmark": "coco",
  "score": 44.1,
  "unit": "AP",
  "provenance": "independent",
  "setting": "val, S size, as reported in RF-DETR paper",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2025-11",
  "sources": [
   "https://arxiv.org/html/2511.09554v2"
  ]
 },
 {
  "model": "ultralytics-yolo11",
  "benchmark": "coco",
  "score": 48.3,
  "unit": "AP",
  "provenance": "independent",
  "setting": "val, M size, as reported in RF-DETR paper",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2025-11",
  "sources": [
   "https://arxiv.org/html/2511.09554v2"
  ]
 },
 {
  "model": "ultralytics-yolo26-l",
  "benchmark": "coco",
  "score": 55,
  "unit": "mAP50-95",
  "provenance": "vendor-reported",
  "setting": "val",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2026-01",
  "sources": [
   "https://docs.ultralytics.com/models/yolo26/"
  ]
 },
 {
  "model": "ultralytics-yolo26-m",
  "benchmark": "coco",
  "score": 53.1,
  "unit": "mAP50-95",
  "provenance": "vendor-reported",
  "setting": "val",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2026-01",
  "sources": [
   "https://docs.ultralytics.com/models/yolo26/"
  ]
 },
 {
  "model": "ultralytics-yolo26-n",
  "benchmark": "coco",
  "score": 40.1,
  "unit": "mAP50-95",
  "provenance": "vendor-reported",
  "setting": "val, end-to-end (NMS-free) mode",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2026-01",
  "sources": [
   "https://docs.ultralytics.com/models/yolo26/"
  ]
 },
 {
  "model": "ultralytics-yolo26-n",
  "benchmark": "coco",
  "score": 40.9,
  "unit": "mAP50-95",
  "provenance": "vendor-reported",
  "setting": "Ultralytics docs",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2026-01",
  "sources": [
   "https://docs.ultralytics.com/models/yolo26/"
  ]
 },
 {
  "model": "ultralytics-yolo26-s",
  "benchmark": "coco",
  "score": 48.6,
  "unit": "mAP50-95",
  "provenance": "vendor-reported",
  "setting": "val",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2026-01",
  "sources": [
   "https://docs.ultralytics.com/models/yolo26/"
  ]
 },
 {
  "model": "ultralytics-yolo26-x",
  "benchmark": "coco",
  "score": 56.9,
  "unit": "mAP50-95",
  "provenance": "vendor-reported",
  "setting": "val, end-to-end (NMS-free) mode",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2026-01",
  "sources": [
   "https://docs.ultralytics.com/models/yolo26/"
  ]
 },
 {
  "model": "ultralytics-yolo26-x",
  "benchmark": "coco",
  "score": 57.5,
  "unit": "mAP50-95",
  "provenance": "vendor-reported",
  "setting": "Ultralytics docs",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2026-01",
  "sources": [
   "https://docs.ultralytics.com/models/yolo26/"
  ]
 },
 {
  "model": "upstage-solar-open-2",
  "benchmark": "gpqa-diamond",
  "score": 86.3,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/upstage/Solar-Open2-250B",
   "https://huggingface.co/upstage"
  ]
 },
 {
  "model": "upstage-solar-open-2",
  "benchmark": "kmmlu-pro",
  "score": 78.4,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/upstage/Solar-Open2-250B",
   "https://huggingface.co/upstage"
  ]
 },
 {
  "model": "upstage-solar-open-2",
  "benchmark": "mmlu-pro",
  "score": 86.2,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/upstage/Solar-Open2-250B",
   "https://huggingface.co/upstage"
  ]
 },
 {
  "model": "upstage-solar-pro-4",
  "benchmark": "aa-intelligence-index",
  "score": 28,
  "unit": "index",
  "provenance": "independent",
  "setting": "listed on AA as Solar Pro 45; asterisk on page",
  "view": "AA leaderboard, 205 current models",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://artificialanalysis.ai/leaderboards/models"
  ]
 },
 {
  "model": "upstage-solar-pro-4",
  "benchmark": "livecodebench",
  "score": 87.8,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": "BenchLM main table",
  "rank": 1,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://www.benchlm.ai/benchmarks/livecodebench"
  ],
  "unverified": []
 },
 {
  "model": "upstage-solar-pro-4",
  "benchmark": "lmarena-text",
  "score": null,
  "unit": "Elo",
  "provenance": "independent",
  "setting": "solar-pro4",
  "view": "Arena Text overall",
  "rank": 182,
  "rank_population": null,
  "date": "2026-10-08",
  "sources": [
   "https://arena.ai/leaderboard/chat/text"
  ]
 },
 {
  "model": "ustc-d-fine",
  "benchmark": "coco",
  "score": 42.7,
  "unit": "AP",
  "provenance": "independent",
  "setting": "val, N size, as reported in RF-DETR paper",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2025-11",
  "sources": [
   "https://arxiv.org/html/2511.09554v2"
  ]
 },
 {
  "model": "ustc-d-fine",
  "benchmark": "coco",
  "score": 50.6,
  "unit": "AP",
  "provenance": "independent",
  "setting": "val, S size, as reported in RF-DETR paper",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2025-11",
  "sources": [
   "https://arxiv.org/html/2511.09554v2"
  ]
 },
 {
  "model": "ustc-d-fine",
  "benchmark": "coco",
  "score": 55,
  "unit": "AP",
  "provenance": "independent",
  "setting": "val, M size, as reported in RF-DETR paper",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2025-11",
  "sources": [
   "https://arxiv.org/html/2511.09554v2"
  ]
 },
 {
  "model": "utopai-studios-utopai-x",
  "benchmark": "aa-video-t2v",
  "score": 1149,
  "unit": "Elo",
  "provenance": "independent",
  "setting": null,
  "view": "AA Text-to-Video leaderboard",
  "rank": 2,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://artificialanalysis.ai/video/leaderboard/text-to-video"
  ]
 },
 {
  "model": "weathermesh4",
  "benchmark": "weatherbench-2",
  "score": 113.8,
  "unit": "RMSE m2/s2",
  "provenance": "maintainer-run",
  "setting": "Z500 day 3, deterministic, WeatherMesh4 vs ERA5",
  "view": "year 2020, 240x121 grid",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://researchsites.withgoogle.com/weatherbench/deterministic/"
  ]
 },
 {
  "model": "weathermesh4",
  "benchmark": "weatherbench-2",
  "score": 250.7,
  "unit": "RMSE m2/s2",
  "provenance": "maintainer-run",
  "setting": "Z500 day 5, deterministic, WeatherMesh4 vs ERA5",
  "view": "year 2020, 240x121 grid",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://researchsites.withgoogle.com/weatherbench/deterministic/"
  ]
 },
 {
  "model": "weathermesh4",
  "benchmark": "weatherbench-2",
  "score": 36.8,
  "unit": "RMSE m2/s2",
  "provenance": "maintainer-run",
  "setting": "Z500 day 1, deterministic, WeatherMesh4 vs ERA5",
  "view": "year 2020, 240x121 grid",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://researchsites.withgoogle.com/weatherbench/deterministic/"
  ]
 },
 {
  "model": "weathermesh4",
  "benchmark": "weatherbench-2",
  "score": 608.1,
  "unit": "RMSE m2/s2",
  "provenance": "maintainer-run",
  "setting": "Z500 day 10, deterministic, WeatherMesh4 vs ERA5",
  "view": "year 2020, 240x121 grid",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://researchsites.withgoogle.com/weatherbench/deterministic/"
  ]
 },
 {
  "model": "wonderworld",
  "benchmark": "worldscore",
  "score": 50.88,
  "unit": "score",
  "provenance": "maintainer-run",
  "setting": "Dynamic aggregate",
  "view": "WorldScore paper table",
  "rank": null,
  "rank_population": null,
  "date": "2025",
  "sources": [
   "https://arxiv.org/html/2504.00983v2"
  ]
 },
 {
  "model": "wonderworld",
  "benchmark": "worldscore",
  "score": 72.69,
  "unit": "score",
  "provenance": "maintainer-run",
  "setting": "Static aggregate",
  "view": "WorldScore paper table",
  "rank": null,
  "rank_population": null,
  "date": "2025",
  "sources": [
   "https://arxiv.org/html/2504.00983v2"
  ]
 },
 {
  "model": "xiaomi-mimo-v2-5-pro",
  "benchmark": "lmarena-text",
  "score": 1468,
  "unit": "Elo",
  "provenance": "independent",
  "setting": null,
  "view": "Arena Text overall",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-08",
  "sources": [
   "https://arena.ai/leaderboard/chat/text"
  ],
  "uncertainty": "±4"
 },
 {
  "model": "xiaomi-mimo-v2-5",
  "benchmark": "aa-intelligence-index",
  "score": 25,
  "unit": "index",
  "provenance": "independent",
  "setting": "Intelligence Index v4.3.2; marked estimated (asterisk) on page",
  "view": "AA model page, rank within model class",
  "rank": 27,
  "rank_population": 117,
  "date": "2026-10-11",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://artificialanalysis.ai/models/mimo-v2-5-0424"
  ]
 },
 {
  "model": "xiaomi-mimo-v2-6-flash",
  "benchmark": "aa-intelligence-index",
  "score": 38,
  "unit": "index",
  "provenance": "independent",
  "setting": "Intelligence Index v4.3.2",
  "view": "AA model page, rank within model class",
  "rank": 8,
  "rank_population": 117,
  "date": "2026-10-11",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://artificialanalysis.ai/models/mimo-v2-6-flash"
  ]
 },
 {
  "model": "xiaomi-mimo-v2-6-flash",
  "benchmark": "automationbench",
  "score": 52.3,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "AutomationBench v1.0.6",
  "view": "MiMo-V2.6 model card comparison table",
  "rank": null,
  "rank_population": null,
  "date": "2026-09-21",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-RL"
  ]
 },
 {
  "model": "xiaomi-mimo-v2-6-flash",
  "benchmark": "deepswe-v1-1",
  "score": 67.9,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": "MiMo-V2.6 model card comparison table",
  "rank": null,
  "rank_population": null,
  "date": "2026-09-21",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-RL"
  ]
 },
 {
  "model": "xiaomi-mimo-v2-6-flash",
  "benchmark": "programbench",
  "score": 26,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": "MiMo-V2.6 model card comparison table",
  "rank": null,
  "rank_population": null,
  "date": "2026-09-21",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-RL"
  ]
 },
 {
  "model": "xiaomi-mimo-v2-6-flash",
  "benchmark": "terminal-bench-2-1",
  "score": 87.6,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": "MiMo-V2.6 model card comparison table",
  "rank": null,
  "rank_population": null,
  "date": "2026-09-21",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-RL"
  ]
 },
 {
  "model": "xiaomi-mimo-v2-6-flash",
  "benchmark": "terminal-bench-4-0",
  "score": 28.8,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": "MiMo-V2.6 model card comparison table",
  "rank": null,
  "rank_population": null,
  "date": "2026-09-21",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-RL"
  ]
 },
 {
  "model": "xiaomi-mimo-v2-6-flash",
  "benchmark": "toolathlon",
  "score": 73.6,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "Toolathlon-Verified",
  "view": "MiMo-V2.6 model card comparison table",
  "rank": null,
  "rank_population": null,
  "date": "2026-09-21",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-RL"
  ]
 },
 {
  "model": "xiaomi-mimo-v2-6-pro",
  "benchmark": "aa-intelligence-index",
  "score": 46,
  "unit": "index",
  "provenance": "independent",
  "setting": null,
  "view": "AA leaderboard, 205 current models",
  "rank": 25,
  "rank_population": 205,
  "date": "2026-10-10",
  "sources": [
   "https://artificialanalysis.ai/leaderboards/models"
  ]
 },
 {
  "model": "xiaomi-mimo-v2-6-pro",
  "benchmark": "aa-intelligence-index",
  "score": 46,
  "unit": "index",
  "provenance": "independent",
  "setting": null,
  "view": "Artificial Analysis open-weights view",
  "rank": 1,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://artificialanalysis.ai/leaderboards/models?open_weights=true",
   "https://artificialanalysis.ai/models/open-source"
  ]
 },
 {
  "model": "xiaomi-mimo-v2-6-pro",
  "benchmark": "deepswe",
  "score": 71.9,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/XiaomiMiMo",
   "https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Pro-RL"
  ]
 },
 {
  "model": "xiaomi-mimo-v2-6-pro",
  "benchmark": "lmarena-text",
  "score": 1480,
  "unit": "Elo",
  "provenance": "independent",
  "setting": null,
  "view": "Arena Text overall",
  "rank": 26,
  "rank_population": null,
  "date": "2026-10-08",
  "sources": [
   "https://arena.ai/leaderboard/chat/text"
  ],
  "uncertainty": "±9"
 },
 {
  "model": "xiaomi-mimo-v2-6-pro",
  "benchmark": "terminal-bench-2-1",
  "score": 89.9,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/XiaomiMiMo",
   "https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Pro-RL"
  ]
 },
 {
  "model": "xiaomi-mimo-v2-flash",
  "benchmark": "aa-intelligence-index",
  "score": 22,
  "unit": "index",
  "provenance": "independent",
  "setting": "Intelligence Index v4.3.2; marked estimated (asterisk) on page; AA entry MiMo-V2-Flash (Feb 2026)",
  "view": "AA model page, rank within model class",
  "rank": 40,
  "rank_population": 117,
  "date": "2026-10-11",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://artificialanalysis.ai/models/mimo-v2-0206"
  ]
 },
 {
  "model": "xiaomi-mimo-v2-flash",
  "benchmark": "aime-2025",
  "score": 94.1,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": "MiMo-V2-Flash model card, post-trained model table",
  "rank": null,
  "rank_population": null,
  "date": "2025-12-16",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://huggingface.co/XiaomiMiMo/MiMo-V2-Flash"
  ]
 },
 {
  "model": "xiaomi-mimo-v2-flash",
  "benchmark": "browsecomp",
  "score": 45.4,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "Without context management",
  "view": "MiMo-V2-Flash model card, post-trained model table",
  "rank": null,
  "rank_population": null,
  "date": "2025-12-16",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://huggingface.co/XiaomiMiMo/MiMo-V2-Flash"
  ]
 },
 {
  "model": "xiaomi-mimo-v2-flash",
  "benchmark": "gpqa-diamond",
  "score": 83.7,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": "MiMo-V2-Flash model card, post-trained model table",
  "rank": null,
  "rank_population": null,
  "date": "2025-12-16",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://huggingface.co/XiaomiMiMo/MiMo-V2-Flash"
  ]
 },
 {
  "model": "xiaomi-mimo-v2-flash",
  "benchmark": "hle",
  "score": 22.1,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "No tools",
  "view": "MiMo-V2-Flash model card, post-trained model table",
  "rank": null,
  "rank_population": null,
  "date": "2025-12-16",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://huggingface.co/XiaomiMiMo/MiMo-V2-Flash"
  ]
 },
 {
  "model": "xiaomi-mimo-v2-flash",
  "benchmark": "livecodebench-v6",
  "score": 80.6,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": "MiMo-V2-Flash model card, post-trained model table",
  "rank": null,
  "rank_population": null,
  "date": "2025-12-16",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://huggingface.co/XiaomiMiMo/MiMo-V2-Flash"
  ]
 },
 {
  "model": "xiaomi-mimo-v2-flash",
  "benchmark": "mmlu-pro",
  "score": 84.9,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": "MiMo-V2-Flash model card, post-trained model table",
  "rank": null,
  "rank_population": null,
  "date": "2025-12-16",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://huggingface.co/XiaomiMiMo/MiMo-V2-Flash"
  ]
 },
 {
  "model": "xiaomi-mimo-v2-flash",
  "benchmark": "swe-bench-multilingual",
  "score": 71.7,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": "MiMo-V2-Flash model card, post-trained model table",
  "rank": null,
  "rank_population": null,
  "date": "2025-12-16",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://huggingface.co/XiaomiMiMo/MiMo-V2-Flash"
  ]
 },
 {
  "model": "xiaomi-mimo-v2-flash",
  "benchmark": "swe-bench-verified",
  "score": 73.4,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": "MiMo-V2-Flash model card, post-trained model table",
  "rank": null,
  "rank_population": null,
  "date": "2025-12-16",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://huggingface.co/XiaomiMiMo/MiMo-V2-Flash"
  ]
 },
 {
  "model": "xiaomi-mimo-v2-flash",
  "benchmark": "terminal-bench-2-0",
  "score": 38.5,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": "MiMo-V2-Flash model card, post-trained model table",
  "rank": null,
  "rank_population": null,
  "date": "2025-12-16",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://huggingface.co/XiaomiMiMo/MiMo-V2-Flash"
  ]
 },
 {
  "model": "xiaomi-mimo-v2-omni",
  "benchmark": "aa-intelligence-index",
  "score": 25,
  "unit": "index",
  "provenance": "independent",
  "setting": "Intelligence Index v4.3.2; marked estimated (asterisk) on page; AA entry MiMo-V2-Omni-0327",
  "view": "AA model page, rank within model class",
  "rank": 161,
  "rank_population": 697,
  "date": "2026-10-11",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://artificialanalysis.ai/models/mimo-v2-omni-0327"
  ]
 },
 {
  "model": "xiaomi-mimo-v2-pro",
  "benchmark": "swe-bench-verified",
  "score": 78,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://leaderboard.steel.dev/leaderboards/swe-bench-verified.md"
  ]
 },
 {
  "model": "yandex-catboost",
  "benchmark": "tabarena",
  "score": 1368,
  "unit": "Elo",
  "provenance": "maintainer-run",
  "setting": "default",
  "view": "All Tasks, no imputation, snapshot 2026-05-06, 59 entries",
  "rank": 20,
  "rank_population": 59,
  "date": "2026-05-06",
  "sources": [
   "https://benchmarklist.com/benchmarks/tabarena_all/"
  ]
 },
 {
  "model": "yandex-catboost",
  "benchmark": "tabarena",
  "score": 1407,
  "unit": "Elo",
  "provenance": "maintainer-run",
  "setting": "tuned",
  "view": "All Tasks, no imputation, snapshot 2026-05-06, 59 entries",
  "rank": 14,
  "rank_population": 59,
  "date": "2026-05-06",
  "sources": [
   "https://benchmarklist.com/benchmarks/tabarena_all/"
  ]
 },
 {
  "model": "yandex-catboost",
  "benchmark": "tabarena",
  "score": 1418,
  "unit": "Elo",
  "provenance": "maintainer-run",
  "setting": "tuned + ensembled",
  "view": "All Tasks, no imputation, snapshot 2026-05-06, 59 entries",
  "rank": 13,
  "rank_population": 59,
  "date": "2026-05-06",
  "sources": [
   "https://benchmarklist.com/benchmarks/tabarena_all/"
  ]
 },
 {
  "model": "yellow-ai-komodo-7b",
  "benchmark": "indommlu",
  "score": 43.2,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "Komodo-7B-Instruct",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/Yellow-AI-NLP/komodo-7b-base"
  ]
 },
 {
  "model": "yhat-labs-chakrats",
  "benchmark": "gift-eval",
  "score": 0.461,
  "unit": "CRPS (geo-mean, normalised to Seasonal Naive)",
  "provenance": "independent",
  "setting": "pretrained; rank is average CRPS rank",
  "view": "Leaderboard rebuilt from the published raw results, 143 entries covering all 97 configurations",
  "rank": 26,
  "rank_population": 143,
  "date": "2026-10-09",
  "sources": [
   "https://huggingface.co/spaces/Salesforce/GIFT-Eval"
  ],
  "leakage": "no",
  "leakage_note": "Test Leak. column: No (ChakraTS (code))"
 },
 {
  "model": "yhat-labs-chakrats",
  "benchmark": "gift-eval",
  "score": 0.67,
  "unit": "MASE (geo-mean, normalised to Seasonal Naive)",
  "provenance": "independent",
  "setting": "pretrained",
  "view": "Leaderboard rebuilt from the published raw results, 143 entries covering all 97 configurations",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-09",
  "sources": [
   "https://huggingface.co/spaces/Salesforce/GIFT-Eval"
  ],
  "leakage": "no",
  "leakage_note": "Test Leak. column: No (ChakraTS (code))"
 },
 {
  "model": "zhipu-zai-glm-4-0520",
  "benchmark": "bfcl",
  "score": 81.76,
  "unit": "score",
  "provenance": "vendor-reported",
  "setting": "Berkeley Function Call overall",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2024-06-18",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://arxiv.org/html/2406.12793v2"
  ]
 },
 {
  "model": "zhipu-zai-glm-4-0520",
  "benchmark": "gpqa",
  "score": 39.9,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2024-06-18",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://arxiv.org/html/2406.12793v2"
  ]
 },
 {
  "model": "zhipu-zai-glm-4-0520",
  "benchmark": "gsm8k",
  "score": 93.3,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2024-06-18",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://arxiv.org/html/2406.12793v2"
  ]
 },
 {
  "model": "zhipu-zai-glm-4-0520",
  "benchmark": "humaneval",
  "score": 78.5,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2024-06-18",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://arxiv.org/html/2406.12793v2"
  ]
 },
 {
  "model": "zhipu-zai-glm-4-0520",
  "benchmark": "ifeval",
  "score": 79.1,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "English, prompt-level strict",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2024-06-18",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://arxiv.org/html/2406.12793v2"
  ]
 },
 {
  "model": "zhipu-zai-glm-4-0520",
  "benchmark": "math",
  "score": 61.3,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2024-06-18",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://arxiv.org/html/2406.12793v2"
  ]
 },
 {
  "model": "zhipu-zai-glm-4-0520",
  "benchmark": "mmlu",
  "score": 83.3,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": "2024-06-18",
  "uncertainty": null,
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://arxiv.org/html/2406.12793v2"
  ]
 },
 {
  "model": "zhipu-zai-glm-4-7-flash",
  "benchmark": "sea-helm",
  "score": 53.76,
  "unit": "score",
  "provenance": "maintainer-run",
  "setting": "Checkpoint GLM-4.7-Flash as listed; release view (data last updated 18 Sep 2026); score is the average of 2000 bootstraps",
  "view": "SEA-HELM leaderboard, 58 models, SEA average",
  "rank": null,
  "rank_population": null,
  "date": "2026-09-18",
  "uncertainty": "95% CI [-0.57, +0.57]",
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://leaderboard.sea-lion.ai/detailed/SEA"
  ]
 },
 {
  "model": "zhipu-zai-glm-4-7-flash",
  "benchmark": "sea-helm",
  "score": 67.89,
  "unit": "score",
  "provenance": "maintainer-run",
  "setting": null,
  "view": "SEA-HELM Indonesian, open-weight models, average of 2,000 bootstraps",
  "rank": 10,
  "rank_population": null,
  "date": "2026-09-18",
  "sources": [
   "https://leaderboard.sea-lion.ai/detailed/ID"
  ],
  "uncertainty": "95% CI [-1.32, +1.27]"
 },
 {
  "model": "zhipu-zai-glm-5-1",
  "benchmark": "lmarena-text",
  "score": 1464,
  "unit": "Elo",
  "provenance": "independent",
  "setting": null,
  "view": "Arena Text overall",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-08",
  "sources": [
   "https://arena.ai/leaderboard/chat/text"
  ],
  "uncertainty": "±4"
 },
 {
  "model": "zhipu-zai-glm-5-2",
  "benchmark": "lmarena-text",
  "score": 1475,
  "unit": "Elo",
  "provenance": "independent",
  "setting": "glm-5.2-max",
  "view": "Arena Text overall",
  "rank": null,
  "rank_population": null,
  "date": "2026-10-08",
  "sources": [
   "https://arena.ai/leaderboard/chat/text"
  ],
  "uncertainty": "±4"
 },
 {
  "model": "zhipu-zai-glm-5-2",
  "benchmark": "swe-bench-pro",
  "score": 62.1,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "max effort",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://rits.shanghai.nyu.edu/ai/glm-5-2-z-ais-open-weights-coder-beats-gpt-5-5-at-1-6-the-cost/"
  ]
 },
 {
  "model": "zhipu-zai-glm-5-2",
  "benchmark": "swe-bench-verified",
  "score": 80,
  "unit": "%",
  "provenance": "independent",
  "setting": "third-party via Thinking Machines",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://leaderboard.steel.dev/leaderboards/swe-bench-verified.md"
  ]
 },
 {
  "model": "zhipu-zai-glm-5-2",
  "benchmark": "tau2-bench",
  "score": 99.1,
  "unit": "%",
  "provenance": "independent",
  "setting": "Artificial Analysis telecom run",
  "view": "BenchLM aggregator, top score",
  "rank": 1,
  "rank_population": null,
  "date": "2026-10-10",
  "sources": [
   "https://www.benchlm.ai/benchmarks/tau2-bench"
  ],
  "unverified": []
 },
 {
  "model": "zhipu-zai-glm-5-2",
  "benchmark": "terminal-bench-2-1",
  "score": 81,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://rits.shanghai.nyu.edu/ai/glm-5-2-z-ais-open-weights-coder-beats-gpt-5-5-at-1-6-the-cost/"
  ]
 },
 {
  "model": "zhipu-zai-glm-5-3-flash",
  "benchmark": "lmarena-text",
  "score": 1475,
  "unit": "Elo",
  "provenance": "independent",
  "setting": null,
  "view": "Arena Text overall",
  "rank": 38,
  "rank_population": null,
  "date": "2026-10-08",
  "sources": [
   "https://arena.ai/leaderboard/chat/text"
  ],
  "uncertainty": "±5"
 },
 {
  "model": "zhipu-zai-glm-5-3",
  "benchmark": "aa-intelligence-index",
  "score": 45,
  "unit": "index",
  "provenance": "independent",
  "setting": "GLM-5.3 (Max)",
  "view": "Artificial Analysis open-weights view",
  "rank": 2,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://artificialanalysis.ai/leaderboards/models?open_weights=true",
   "https://artificialanalysis.ai/models/open-source"
  ]
 },
 {
  "model": "zhipu-zai-glm-5-3",
  "benchmark": "aa-intelligence-index",
  "score": 45,
  "unit": "index",
  "provenance": "independent",
  "setting": "max",
  "view": "AA leaderboard, 205 current models",
  "rank": 29,
  "rank_population": 205,
  "date": "2026-10-10",
  "sources": [
   "https://artificialanalysis.ai/leaderboards/models"
  ]
 },
 {
  "model": "zhipu-zai-glm-5-3",
  "benchmark": "deepswe-v1-1",
  "score": 66.9,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "mini-swe-agent",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/zai-org/GLM-5.3"
  ]
 },
 {
  "model": "zhipu-zai-glm-5-3",
  "benchmark": "hle",
  "score": 62.5,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "with tools",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/zai-org/GLM-5.3"
  ]
 },
 {
  "model": "zhipu-zai-glm-5-3",
  "benchmark": "lmarena-text",
  "score": 1478,
  "unit": "Elo",
  "provenance": "independent",
  "setting": "glm-5.3-max",
  "view": "Arena Text overall",
  "rank": 27,
  "rank_population": null,
  "date": "2026-10-08",
  "sources": [
   "https://arena.ai/leaderboard/chat/text"
  ],
  "uncertainty": "±5"
 },
 {
  "model": "zhipu-zai-glm-5-3",
  "benchmark": "terminal-bench-2-1",
  "score": 88.2,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/zai-org/GLM-5.3"
  ]
 },
 {
  "model": "zhipu-zai-glm-5-3",
  "benchmark": "terminal-bench-2-1",
  "score": 88.2,
  "unit": "%",
  "provenance": "vendor-reported",
  "setting": "Claude Code 2.1.207",
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/zai-org/GLM-5.3"
  ]
 },
 {
  "model": "zhipu-zai-glm-5-3",
  "benchmark": "terminal-bench-3-0",
  "score": 28.3,
  "unit": null,
  "provenance": "vendor-reported",
  "setting": null,
  "view": null,
  "rank": null,
  "rank_population": null,
  "date": null,
  "sources": [
   "https://huggingface.co/zai-org/GLM-5.3"
  ]
 },
 {
  "model": "zhipu-zai-glm-image",
  "benchmark": "aa-image-t2i-v2-0",
  "score": 891,
  "unit": "Elo",
  "provenance": "independent",
  "setting": null,
  "view": "AA Text-to-Image leaderboard, overall",
  "rank": 107,
  "rank_population": null,
  "date": "2026-10-11",
  "uncertainty": "+-7; 95% interval 884 to 898",
  "leakage": null,
  "leakage_note": null,
  "sources": [
   "https://artificialanalysis.ai/image/leaderboard/text-to-image"
  ]
 },
 {
  "model": "zhipu-zai-glm-ocr",
  "benchmark": "omnidocbench-v1-6",
  "score": 95.22,
  "unit": "score",
  "provenance": "vendor-reported",
  "setting": "overall",
  "view": "PaddleOCR-VL-1.6 paper table",
  "rank": null,
  "rank_population": null,
  "date": "2026-06-02",
  "sources": [
   "https://arxiv.org/pdf/2606.03264"
  ]
 },
 {
  "model": "zhipu-zai-glm-ocr",
  "benchmark": "real5-omnidocbench",
  "score": 90.32,
  "unit": "score",
  "provenance": "vendor-reported",
  "setting": "overall",
  "view": "PaddleOCR-VL-1.6 paper table",
  "rank": null,
  "rank_population": null,
  "date": "2026-06-02",
  "sources": [
   "https://arxiv.org/pdf/2606.03264"
  ]
 }
]