BrowseComp
Web browsing agent tasks
agents and tool usecrowded
Definition
- Version
- not in the notes
- Category
- agents and tool use
- Maintainer
- OpenAI
- Status
- crowded
- Home page
- https://arxiv.org/abs/2504.12516
Sources
- MiniMax M3 - Coding & Agentic Frontier, 1M Context, Multimodal minimax.io https://www.minimax.io/models/text/m3
- huggingface.co/moonshotai/Kimi-K3 https://huggingface.co/moonshotai/Kimi-K3
- BrowseComp: A Simple Yet Challenging Benchmark for Browsing Agents arxiv.org https://arxiv.org/abs/2504.12516
- BrowseComp Leaderboard & Scores , October 2026 benchlm.ai https://www.benchlm.ai/benchmarks/browsecomp
Scores at a Glance
Score in %
Higher is better for this unit.
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
| Model | Score | Who ran it | Setting | View or population | Date | Source |
|---|---|---|---|---|---|---|
 Atria Dawn Preview | 92.5 % | vendor-reported | – | rank 1, BenchLM aggregator, top score | 10 Oct 2026 | benchlm.ai |
 Kimi K3 | 91.2 % | vendor-reported | – | – | – | huggingface.co |
 MiniMax-M3 | 83.5 % | vendor-reported | – | – | – | minimax.io |
 MiMo-V2-Flash | 45.4 % | vendor-reported | Without context management | MiMo-V2-Flash model card, post-trained model table | 16 Dec 2025 | huggingface.co |
 DeepSeek-V3.1-Terminus | 38.5 % | vendor-reported | Model card comparison table; mode not stated | DeepSeek-V3.1-Terminus model card | 22 Sep 2025 | huggingface.co |
| DeepSeek-V3.1 | 30 % | vendor-reported | Thinking mode, internal search agent framework | DeepSeek-V3.1 model card | 21 Aug 2025 | huggingface.co |
 A.X K2 | 9.3 % | vendor-reported | Thinking mode; At most 10 searches | A.X K2 model card | Jul 2026 | huggingface.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, "BrowseComp", https://aurion.semai.id/benchmarks/browsecomp/, records of October 2026.