- Context
- 1Mtokens
- Released
- 5mo 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
Not ranked on Arena Text yet
Arena WebDev
Best Arena rating per model · Higher is better
Arena #64
- 1688
Kimi K3.1 ProSimilar price - 1679
GPT-6.1 TerraSimilar price - 1655
Muse Spark 1.3Similar price - 1520GPT-5.6 TerraNearby rank
- 1519GPT-5.6 LunaNearby rank
- 1515
Qwen3.7 Max - 1512GPT-5.5Nearby rank
- 1509Kimi K2.6Nearby rank
- 1508
GLM 5.1Similar price - 1461Qwen3.6 PlusEarlier version
+54 vs Qwen3.6 Plus (earlier version) · 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 #47
- +0.120GPT-6.1 TerraSimilar price
- +0.049Kimi K3.1 ProSimilar price
- +0.022Muse Spark 1.3Similar price
- -0.054
Mistral Large 4Nearby rank - -0.059
Beam 1.0 501B A23BNearby rank - -0.072Qwen3.7 Max
- -0.076
Hy3Nearby rank - -0.080Qwen3.7 PlusNearby rank
- -0.173
InklingSimilar price
Ahead of 1 of 4 similarly priced models
FrontierMath-Tier-4-v2-Private
Best score per model · Higher is better
#30 of 72
- 92.7%GPT-6.1 TerraSimilar price
- 46.3%Muse Spark 1.3Similar price
- 39.0%Kimi K3Nearby rank
- 36.6%
Gemini 3.7 FlashNearby rank - 34.1%Qwen3.7 Max
- 34.1%Qwen3.8 Max (0902)Nearby rank
- 31.7%
Claude Opus 4.7Nearby rank - 29.3%GLM 5.2Similar price
- 4.9%InklingSimilar price
Ahead of 2 of 4 similarly priced models
FrontierMath-Tiers-1-3-v2-Private
Best score per model · Higher is better
#38 of 87
- 90.9%GPT-6.1 TerraSimilar price
- 74.4%Muse Spark 1.3Similar price
- 65.6%Qwen3.8 Max (0902)Nearby rank
- 64.6%
DeepSeek V4 Pro 0813Nearby rank - 64.6%Qwen3.7 Max
- 62.8%Gemini 3.5 FlashNearby rank
- 59.6%Gemini 3.1 Pro PreviewNearby rank
- 36.8%GLM 5.1Similar price
- 33.3%InklingSimilar price
- 18.9%
Qwen3 MaxPredecessor
+45.6 pts vs Qwen3 Max (predecessor) · Ahead of 2 of 4 similarly priced models
GPQA diamond
Best score per model · Higher is better
#33 of 161
- 94.3%GPT-6.1 TerraSimilar price
- 90.9%DeepSeek V4 Pro 0423Nearby rank
- 90.9%
MiniMax M3Nearby rank - 90.9%Qwen3.7 Max
- 90.9%GLM 5.3Nearby rank
- 90.8%Kimi K2.6Nearby rank
- 89.9%GLM 5.1Similar price
- 88.3%InklingSimilar price
- 72.6%Qwen3 MaxPredecessor
- 71.2%Claude Haiku 4.5Similar price
+18.3 pts vs Qwen3 Max (predecessor) · Ahead of 3 of 4 similarly priced models
OTIS Mock AIME 2024-2025
Best score per model · Higher is better
#38 of 158
- 100.0%GPT-6.1 TerraSimilar price
- 99.2%Muse Spark 1.3Similar price
- 95.6%Gemini 3.5 FlashNearby rank
- 95.6%Kimi K2.7 CodeNearby rank
- 95.6%Qwen3.7 Max
- 94.7%Claude Sonnet 5Nearby rank
- 94.4%Claude Opus 4.6Nearby rank
- 93.3%GLM 5.1Similar price
- 73.3%Qwen3 MaxPredecessor
- 66.7%Claude Haiku 4.5Similar price
+22.2 pts vs Qwen3 Max (predecessor) · Ahead of 2 of 4 similarly priced models
SimpleQA Verified
Best score per model · Higher is better
#23 of 87
- 60.3%Muse Spark 1.2Similar price
- 57.3%GPT-6.1 TerraSimilar price
- 56.0%
Grok 4.7Nearby rank - 55.8%Qwen3.7 Max
- 53.0%Claude Opus 4.8Nearby rank
- 52.9%DeepSeek V4 Pro 0813Nearby rank
- 48.7%Qwen3 MaxPredecessor
- 34.0%GLM 5.1Similar price
- 13.2%Claude Haiku 4.5Similar price
+7.0 pts vs Qwen3 Max (predecessor) · Ahead of 2 of 4 similarly priced models
SWE-bench Verified
Best score per model · Higher is better
#5 of 35
- 79.3%Gemini 3.5 FlashSimilar price
- 78.7%GLM 5.2Nearby rank
- 77.6%DeepSeek V4 Pro 0423Nearby rank
- 77.3%Qwen3.7 Max
- 76.9%GPT-5.4Nearby rank
- 76.7%Qwen3.6 Max PreviewNearby rank
- 76.7%Kimi K2.6Similar price
- 74.2%GLM 5.1Similar price
- 73.6%GPT-5Similar price
- 57.9%Qwen3.6 PlusEarlier version
+19.4 pts vs Qwen3.6 Plus (earlier version) · Ahead of 3 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 WebDevArena #641515
+54 vs Qwen3.6 Plus (earlier version)
- default151595% CI 1508 to 1522 · 8,743 votes
- Agent ArenaArena #47-0.072
- default-0.07295% CI -0.084 to -0.059 · 2,305,379 observations
- FrontierMath-Tier-4-v2-Private#30 of 7234.1%
- default34.1%
Source:Epoch AI evaluation - FrontierMath-Tiers-1-3-v2-Private#38 of 8764.6%
+45.6 pts vs Qwen3 Max (predecessor)
- default64.6%
Source:Epoch AI evaluation - GPQA diamond#33 of 16190.9%
+18.3 pts vs Qwen3 Max (predecessor)
- default90.9%
Source:Epoch AI evaluation - OTIS Mock AIME 2024-2025#38 of 15895.6%
+22.2 pts vs Qwen3 Max (predecessor)
- default95.6%
Source:Epoch AI evaluation - SimpleQA Verified#23 of 8755.8%
+7.0 pts vs Qwen3 Max (predecessor)
- default55.8%
Source:Epoch AI evaluation - SWE-bench Verified#5 of 3577.3%
+19.4 pts vs Qwen3.6 Plus (earlier version)
- default77.3%
Source:Epoch AI evaluation
Benchmark compilation: Epoch AI, Capabilities & benchmarking (CC BY attribution). Scores are converted to percentages and model names matched to the Vertical Tabs catalog. Individual evaluations are credited to their original sources. External results may carry separate licences and evaluation configurations; do not interpret scores from different harnesses as directly comparable.
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.