- input
- $0.15
- cached
- $0.03
- output
- $0.60
- Context
- 524Ktokens
- Released
- 3mo ago
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 #186
- 1452
Gemma 4 31BSimilar price - 1409
Hy3 previewSimilar price - 1390
GPT-5 MiniNearby rank - 1388
Claude Sonnet 3.7Nearby rank - 1387
Solar Pro 4 - 1387
Mistral Medium 3Nearby rank - 1383GPT-4.1 MiniNearby rank
- 1352gpt-oss-120bSimilar price
- 1251
Command R (08-2024)Similar price
Ahead of 2 of 4 similarly priced models
Arena WebDev
Best Arena rating per model · Higher is better
Arena #118
- 1664
DeepSeek V4.1 Flash 1017Similar price - 1609
Muse EmberSimilar price - 1386
MiniMax M2.5Nearby rank - 1370Gemma 4 31BSimilar price
- 1369Solar Pro 4
- 1362DeepSeek V3.2Nearby rank
- 1360
Qwen3.5-122B-A10BNearby rank - 1358Hy3 previewSimilar price
Ahead of 0 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 #59
- +0.020DeepSeek V4.1 Flash 1017Similar price
- +0.017Muse EmberSimilar price
- +0.016GPT-6 LunaSimilar price
- -0.076Hy3Similar price
- -0.173
InklingNearby rank - -0.181Inkling SmallNearby rank
- -0.226Solar Pro 4
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 #1861387
- default138795% CI 1382 to 1393 · 27,104 votes
- Arena WebDevArena #1181369
- default136995% CI 1359 to 1380 · 4,501 votes
- Agent ArenaArena #59-0.226
- default-0.22695% CI -0.248 to -0.204 · 567,924 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.