- Context
- 1Mtokens
- Released
- 1y ago
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 #194
- 1456
Claude Sonnet 4.5Similar release date - 1423
Qwen3 MaxSimilar release date - 1416
DeepSeek V3.1 TerminusSimilar release date - 1413
Qwen3 VL 235B A22B InstructSimilar release date - 1383
GPT-4.1 MiniNearby rank - 1382Qwen3 30B A3B Instruct 2507Nearby rank
- 1379
Gemini 2.5 Flash-Lite Preview 09-2025 - 1379
Trinity Large PreviewNearby rank - 1378
GLM 4.6VNearby rank
Ahead of 0 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 Vision
Best Arena rating per model · Higher is better
Arena #108
- 1214Qwen3 VL 235B A22B InstructSimilar release date
- 1188Qwen3 VL 235B A22B ThinkingSimilar release date
- 1185GPT-5 MiniNearby rank
- 1174Gemini 2.5 Flash-Lite Preview 09-2025
- 1172Gemini 2.0 FlashNearby rank
- 1162GPT-4o (2024-05-13)Nearby rank
- 1160
Mistral Medium 3.1Similar release date - 1153GLM 4.5VSimilar release date
Ahead of 1 of 4 models released around the same time
Arena Search
Best Arena rating per model · Higher is better
Not ranked on Arena Search yet
Arena Document
Best Arena rating per model · Higher is better
Not ranked on Arena Document 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 #1941379
- default1379non-thinking95% CI 1376 to 1383 · 47,219 votes
- Arena VisionArena #1081174
- default1174non-thinking95% CI 1165 to 1184 · 4,849 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.