Project AURIONAI Use-Cases Research & Innovation

LiveCodeBench

coding.

v6coding
5scores
5models
0independent
0maintainer-run
5vendor-reported

Definition

Version
v6
Category
coding
Maintainer
not in the notes
Status
not in the notes
Home page
not in the notes

Sources

  1. Qwen/Qwen3.8-Flash-Next , Hugging Face huggingface.co https://huggingface.co/Qwen/Qwen3.8-Flash-Next

Scores at a Glance

Score in %

Higher is better for this unit.

1Alibaba (Qwen)Qwen3.8-Flash-NextAlibaba (Qwen)
91.9 %
vendor-reported2Alibaba (Qwen)Qwen3.8-27BAlibaba (Qwen)
90.3 %
vendor-reported
0255075100
Where this comes from
Each bar is one model, with its most independent recorded score. Hatched bars are vendor-reported; the word beside each bar says who ran it. Settings and dates differ between rows; the Scores table below has every result.

Scores

5 of 5 scores shown livecodebench-v6-scores.csv
ModelScoreWho ran itSettingView or populationDateSource
Alibaba (Qwen)Qwen3.8-Flash-Next91.9 %vendor-reported–––huggingface.co
Alibaba (Qwen)Qwen3.8-27B90.3 %vendor-reported–––huggingface.co
SK TelecomA.X K284 %vendor-reportedThinking mode; Feb to May windowA.X K2 model cardJul 2026huggingface.co
XiaomiMiMo-V2-Flash80.6 %vendor-reported–MiMo-V2-Flash model card, post-trained model table16 Dec 2025huggingface.co
LG AI ResearchEXAONE 4.0 (32B)66.7 %vendor-reportedReasoning modeEXAONE 4.0 model cardJul 2025huggingface.co
Where this comes from
Scores from different settings, harnesses or dates are not directly comparable; the row says which. Sorted by score, highest first, as a reading aid, not a ranking.

To cite this page: Project AURION, AI Use-Cases Research & Innovation, "LiveCodeBench", https://aurion.semai.id/benchmarks/livecodebench-v6/, records of October 2026.