- Context
- 131Ktokens
- Released
- 2y ago
- Size
- 8Bparameters
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 #331
- 1374
Claude Sonnet 3.5 v2Similar release date - 1303
Qwen2.5 72B InstructSimilar release date - 1267
Aya Expanse 32BSimilar release date - 1251Command R (08-2024)Nearby rank
- 1241
Nova Micro 1.0Nearby rank - 1238
Ministral 8B Instruct - 1230Mixtral 8x22B InstructNearby rank
- 1223Aya Expanse 8BNearby rank
- 1167
Llama 3.2 3B InstructSimilar release date
Ahead of 1 of 4 models released around the same time
Arena WebDev
Best Arena rating per model · Higher is better
Not ranked on Arena WebDev 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
Not ranked on Agent Arena yet
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 #3311238
- default123895% CI 1229 to 1247 · 4,781 votes
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.