- input
- $0.0825
- cached
- $0.0206
- output
- $0.33
- Context
- 262Ktokens
- Released
- 4mo ago
- Size
- 299Bparameters
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
Arena #76
- 1455
Qwen3.7 PlusNearby rank - 1455
Gemini 3.5 Flash LiteNearby rank - 1454
Hy3 - 1453
GPT-5.6 LunaNearby rank - 1452Gemma 4 31BNearby rank
- 1393
Step 3.5 FlashSimilar price - 1382Qwen3 30B A3B Instruct 2507Similar price
- 1365Gemma 3 27BSimilar price
- 1364
GLM 4.7 FlashSimilar price
Ahead of 4 of 4 similarly priced models
Arena WebDev
Best Arena rating per model · Higher is better
Arena #68
- 1638
MiMo-V2.6-FlashSimilar price - 1585
MiniMax M3.1 FlashSimilar price - 1509
Kimi K2.6Nearby rank - 1508GLM 5.1Nearby rank
- 1506Hy3
- 1500Gemini 3.5 FlashNearby rank
- 1493
Claude Opus 4.5Nearby rank - 1358Gemma 4 26B A4BSimilar price
- 1244Qwen3.5-FlashSimilar price
Ahead of 2 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 #48
- +0.017
Muse EmberSimilar price - +0.016GPT-6 LunaSimilar price
- -0.000MiMo-V2.6-FlashSimilar price
- -0.027MiniMax M3.1 FlashSimilar price
- -0.059
Beam 1.0 501B A23BNearby rank - -0.072Qwen3.7 MaxNearby rank
- -0.076Hy3
- -0.080Qwen3.7 PlusNearby rank
- -0.080Muse Spark 1.1Nearby rank
Ahead of 0 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 TextArena #761454
- default145495% CI 1449 to 1460 · 15,068 votes
- Arena WebDevArena #681506
- default150695% CI 1498 to 1514 · 7,259 votes
- Agent ArenaArena #48-0.076
- default-0.07695% CI -0.090 to -0.061 · 1,236,393 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.