- input
- $0.7506
- cached
- $0.0378
- output
- $2.2509
- Context
- 1Mtokens
- Released
- 2mo ago
- Size
- 780Bparameters
Cost/1M tokens
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 #25
- 1641
Grok 4.7Nearby rank - 1638
MiMo-V2.6-FlashNearby rank - 1632
Hy4 preview - 1625
Claude Fable 5Nearby rank - 1624MiMo-V2.6-ProNearby rank
- 1564
Mistral Large 4Similar price - 1448
DeepSeek V4 Pro 0423Similar price - 1436
Kimi K2.5Similar price - 1435
GLM 4.7Similar price
Ahead of 4 of 4 similarly priced models
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 #30
- +0.006Kimi K3Nearby rank
- +0.005Claude Haiku 5.5Nearby rank
- +0.005Hy4 preview
- +0.002GLM 5.2Nearby rank
- +0.001
Qwen3.8 MaxNearby rank - -0.022
Gemini 3.7 FlashSimilar price - -0.037
Step 5 PreviewSimilar price - -0.054Mistral Large 4Similar price
- -0.156
Nemotron 3 UltraSimilar price
Ahead of 4 of 4 similarly priced models
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 #251632
- default163295% CI 1622 to 1641 · 4,602 votes
- Agent ArenaArena #30+0.005
- default+0.00595% CI -0.003 to +0.012 · 12,372,968 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.