- Context
- 2Mtokens
- Released
- 11mo 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 #116
- 1486
Gemini 3 Pro PreviewSimilar release date - 1474
Claude Opus 4.5Similar release date - 1455
GPT-5.1Similar release date - 1433Gemini 3.1 Flash Lite PreviewNearby rank
- 1432o3Nearby rank
- 1431
Grok 4.1 Fast (Reasoning) - 1430
MiMo-V2-OmniNearby rank - 1430
Kimi K2 Thinking TurboNearby rank - 1405X-Ai/Grok-4-Fast-ReasoningPredecessor
- 1306
Olmo 3 32B ThinkSimilar release date
+25 vs X-Ai/Grok-4-Fast-Reasoning (predecessor) · Ahead of 1 of 4 models released around the same time
Arena WebDev
Best Arena rating per model · Higher is better
Arena #146
- 1493Claude Opus 4.5Similar release date
- 1441Gemini 3 Pro PreviewSimilar release date
- 1397GPT-5.1Similar release date
- 1362
DeepSeek V3.2Similar release date - 1245GPT-5.1-Codex-MiniNearby rank
- 1244
Qwen3.5-FlashNearby rank - 1242Grok 4.1 Fast (Reasoning)
- 1233
Mistral Large 3 2512Nearby rank - 1228Gemini 2.5 ProNearby rank
- 1162X-Ai/Grok-4-Fast-ReasoningPredecessor
+80 vs X-Ai/Grok-4-Fast-Reasoning (predecessor) · Ahead of 0 of 4 models released around the same time
Arena Vision
Best Arena rating per model · Higher is better
Arena #96
- 1289Gemini 3 Pro PreviewSimilar release date
- 1251GPT-5.1Similar release date
- 1200Mistral Large 3 2512Similar release date
- 1199Mistral Medium 3.5Nearby rank
- 1199GPT-5.4 NanoNearby rank
- 1196Grok 4.1 Fast (Reasoning)
- 1193Claude Sonnet 3.7Nearby rank
- 1189Gemini 2.5 Flash-Lite Preview 06-17Nearby rank
- 1161
GLM 4.6VSimilar 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
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 #1161431
+25 vs X-Ai/Grok-4-Fast-Reasoning (predecessor)
- default1431reasoning95% CI 1427 to 1434 · 57,133 votes
- Arena WebDevArena #1461242
+80 vs X-Ai/Grok-4-Fast-Reasoning (predecessor)
- default1242reasoning95% CI 1231 to 1253 · 5,435 votes
- Arena VisionArena #961196
- default1196reasoning95% CI 1190 to 1203 · 13,295 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.