- Context
- 262Ktokens
- Released
- 2mo ago
- Size
- —parameters
Benchmarks
DeepSWE is the primary coding benchmark where an exact model evaluation exists. Arena leaderboards and other sourced evaluations appear below; missing scores are not zero.
How it ranks
Against its predecessor, similarly priced models and the models ranked around it.
DeepSWE 1.1
Best pass@1 per model · Higher is better
Not evaluated in DeepSWE 1.1
Arena Text
Best Arena rating per model · Higher is better
Not ranked on Arena Text yet
Arena WebDev
Best Arena rating per model · Higher is better
Arena #28
- 1742
Claude Fable 5.1Similar release date - 1676
Qwen3.8 Max (0902)Similar release date - 1632
Hy4 previewSimilar release date - 1625Claude Fable 5Nearby rank
- 1624
MiMo-V2.6-ProNearby rank - 1624
Qwen3.8 Flash Next - 1622
GLM 5.3Nearby rank - 1621
DeepSeek V4.1 FlashNearby rank - 1609GLM 5.3 FlashSimilar release date
Ahead of 1 of 4 models released around the same time
Arena Vision
Best Arena rating per model · Higher is better
Not ranked on Arena Vision yet
Arena Search
Best Arena rating per model · Higher is better
Not ranked on Arena Search yet
Agent Arena
Best IPS score per model · Higher is better
Arena #42
- +0.148Claude Fable 5.1Similar release date
- +0.023
Gemini 3.8 FlashSimilar release date - +0.005Hy4 previewSimilar release date
- -0.029GLM 5.3 FlashSimilar release date
- -0.037
Step 5 PreviewNearby rank - -0.045Gemini 3.1 Pro PreviewNearby rank
- -0.046Qwen3.8 Flash Next
- -0.048Qwen3.8 27BNearby rank
- -0.054
Mistral Large 4Nearby rank
Ahead of 0 of 4 models released around the same time
Not evaluated in DeepSWE 1.1 as of 2026-09-22. Results are only shown for exact model versions in the official dataset. Official leaderboard.
All published scores
- Arena WebDevArena #281624
- default162495% CI 1616 to 1631 · 11,325 votes
- Agent ArenaArena #42-0.046
- default-0.04695% CI -0.054 to -0.039 · 17,165,058 observations
Arena ratings: Arena (lmarena-ai/leaderboard-dataset), licensed CC BY 4.0. Ratings come from pairwise human votes and are only comparable within one leaderboard; the interval is Arena's 95% confidence interval. Model names are matched to the Vertical Tabs catalog.