- input
- $0.351
- output
- $0.555
- Context
- 128Ktokens
- Released
- 1y ago
- Size
- 24Bparameters
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 #291
- 1483
GLM 5.3Similar price - 1417
DeepSeek V3.1Similar price - 1415
MiniMax M2.7Similar price - 1346
Qwen-PlusSimilar price - 1303
Gemma 3 4BNearby rank - 1303Qwen2.5 72B InstructNearby rank
- 1303
Mistral Small 3.1 24B - 1299
Llama 3.1 Nemotron 70B InstructNearby rank - 1293
Llama 3.1 70B InstructNearby rank - 1274Mistral Small 3Predecessor
+28 vs Mistral Small 3 (predecessor) · Ahead of 0 of 4 similarly priced models
Arena WebDev
Best Arena rating per model · Higher is better
Not ranked on Arena WebDev yet
Arena Vision
Best Arena rating per model · Higher is better
Arena #129
- 1263DeepSeek V4.1 FlashSimilar price
- 1255
GPT-5.6 LunaSimilar price - 1161GLM 4.6VSimilar price
- 1145Llama 4 MaverickSimilar price
- 1128Llama 4 ScoutNearby rank
- 1127
Claude Haiku 3.5Nearby rank - 1127Mistral Small 3.1 24B
- 1121Qwen2.5 VL 72B InstructNearby rank
- 1118GPT-4o (2024-08-06)Nearby rank
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
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 #2911303
+28 vs Mistral Small 3 (predecessor)
- default130395% CI 1298 to 1307 · 32,666 votes
- Arena VisionArena #1291127
- default112795% CI 1118 to 1135 · 28,452 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.