- input
- $2.00
- cached
- $0.50
- output
- $8.00
- Context
- 1Mtokens
- Released
- 1y 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
Arena #147
- 1472
Claude Sonnet 5.5Similar price - 1466
Grok 4.5Similar price - 1446
Gemini 2.5 ProSimilar price - 1427
Mistral Medium 3.5Similar price - 1415
MiniMax M2.7Nearby rank - 1415Mistral Large 3 2512Nearby rank
- 1415
GPT-4.1 - 1414Claude Haiku 4.5Nearby rank
- 1413
Qwen3 VL 235B A22B InstructNearby rank - 1336GPT-4o (2024-08-06)Earlier version
+79 vs GPT-4o (2024-08-06) (earlier version) · 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 #85
- 1280Grok 4.5Similar price
- 1263Claude Sonnet 5.5Similar price
- 1247Gemini 2.5 ProSimilar price
- 1215Gemini 2.5 FlashNearby rank
- 1214Qwen3 VL 235B A22B InstructNearby rank
- 1214GPT-4.1
- 1211GPT-5Nearby rank
- 1208Claude Opus 4Nearby rank
- 1199Mistral Medium 3.5Similar price
- 1118GPT-4o (2024-08-06)Earlier version
+95 vs GPT-4o (2024-08-06) (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
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
ARC-AGI-2
Best score per model · Higher is better
#77 of 85
- 83.9%Claude Sonnet 5.5Similar price
- 67.1%Grok 4.6Similar price
- 60.4%
Kimi K3Similar price - 4.9%Gemini 2.5 ProSimilar price
- 1.1%
R1 0528Nearby rank - 0.9%Claude Sonnet 3.7Nearby rank
- 0.4%GPT-4.1
- 0.0%Gemini 2.5 Pro Preview 06-05Nearby rank
- 0.0%
Llama 4 MaverickNearby rank - 0.0%GPT-4o (2024-11-20)Predecessor
+0.4 pts vs GPT-4o (2024-11-20) (predecessor) · Ahead of 0 of 4 similarly priced models
FrontierMath-2025-02-28-Private
Best score per model · Higher is better
#40 of 58
- 33.4%
GLM 5.1Similar price - 32.4%Claude Sonnet 4.6Similar price
- 14.1%Gemini 2.5 ProSimilar price
- 10.3%Gemini 2.5 Pro Preview 06-05Similar price
- 6.2%Qwen3.5-FlashNearby rank
- 5.9%Claude Haiku 4.5Nearby rank
- 5.5%GPT-4.1
- 4.8%Gemini 2.5 FlashNearby rank
- 4.5%Claude Opus 4Nearby rank
- 0.3%GPT-4o (2024-11-20)Predecessor
+5.2 pts vs GPT-4o (2024-11-20) (predecessor) · Ahead of 0 of 4 similarly priced models
FrontierMath-Tier-4-2025-07-01-Private
Best score per model · Higher is better
#39 of 46
- 12.5%GLM 5.1Similar price
- 8.3%Claude Sonnet 4.6Similar price
- 4.2%Gemini 2.5 ProSimilar price
- 2.1%Gemini 2.5 Pro Preview 06-05Similar price
- 0.0%Claude Sonnet 4Nearby rank
- 0.0%Kimi K2 ThinkingNearby rank
- 0.0%GPT-4.1
- 0.0%Qwen3 235B A22B Thinking 2507Nearby rank
- 0.0%Qwen3.5-FlashNearby rank
Ahead of 0 of 4 similarly priced models
FrontierMath-Tiers-1-3-v2-Private
Best score per model · Higher is better
#85 of 87
- 88.8%Claude Sonnet 5.5Similar price
- 66.0%Grok 4.6Similar price
- 65.6%Qwen3.8 Max (0902)Similar price
- 24.6%Gemini 2.5 ProSimilar price
- 12.6%Claude Opus 4.1Nearby rank
- 6.7%GPT-4.1 MiniNearby rank
- 6.0%GPT-4.1
- 0.7%GPT-4o-mini (2024-07-18)Nearby rank
- 0.4%GPT-4o (2024-08-06)Earlier version
+5.6 pts vs GPT-4o (2024-08-06) (earlier version) · Ahead of 0 of 4 similarly priced models
GPQA diamond
Best score per model · Higher is better
#113 of 161
- 95.6%Claude Sonnet 5.5Similar price
- 94.0%Grok 4.6Similar price
- 92.3%Qwen3.8 Max (0902)Similar price
- 85.3%Gemini 2.5 ProSimilar price
- 69.4%GPT-5 NanoNearby rank
- 67.6%DeepSeek V3 0324Nearby rank
- 66.9%GPT-4.1
- 65.8%GPT-4.1 MiniNearby rank
- 65.7%Qwen3 32BNearby rank
- 47.9%GPT-4o (2024-11-20)Predecessor
+19.0 pts vs GPT-4o (2024-11-20) (predecessor) · Ahead of 0 of 4 similarly priced models
Humanity's Last Exam
Best score per model · Higher is better
#31 of 34
- 46.4%Gemini 3.1 Pro PreviewSimilar price
- 46.1%Claude Sonnet 5.5Similar price
- 21.6%Gemini 2.5 Pro Preview 06-05Similar price
- 7.5%Claude Sonnet 4.5Similar price
- 5.7%Llama 4 MaverickNearby rank
- 5.5%Claude Sonnet 4Nearby rank
- 5.4%GPT-4.1
- 4.5%Mistral Medium 3Nearby rank
- 4.1%Claude Sonnet 3.5 v2Nearby rank
- 2.7%GPT-4o (2024-11-20)Predecessor
+2.7 pts vs GPT-4o (2024-11-20) (predecessor) · Ahead of 0 of 4 similarly priced models
OTIS Mock AIME 2024-2025
Best score per model · Higher is better
#124 of 158
- 100.0%Claude Sonnet 5.5Similar price
- 100.0%Qwen3.8 Max (0902)Similar price
- 99.2%Grok 4.6Similar price
- 84.7%Gemini 2.5 ProSimilar price
- 44.7%GPT-4.1 MiniNearby rank
- 43.9%DeepSeek R1 0528 Qwen3 8BNearby rank
- 38.3%GPT-4.1
- 37.8%DeepSeek V3 0324Nearby rank
- 32.2%Mistral Medium 3Nearby rank
- 6.3%GPT-4o (2024-11-20)Predecessor
+32.1 pts vs GPT-4o (2024-11-20) (predecessor) · Ahead of 0 of 4 similarly priced models
SimpleQA Verified
Best score per model · Higher is better
#65 of 87
- 66.2%Gemini 3.5 FlashSimilar price
- 56.0%Grok 4.7Similar price
- 47.3%Qwen3.8 Max (0902)Similar price
- 46.5%Claude Sonnet 5.5Similar price
- 33.2%Grok 4.3Nearby rank
- 32.2%GLM 4.7Nearby rank
- 31.1%GPT-4.1
- 30.7%Claude Sonnet 4.5Nearby rank
- 30.2%Grok 4.20 (Reasoning)Nearby rank
- 26.0%GPT-4o (2024-08-06)Earlier version
+5.1 pts vs GPT-4o (2024-08-06) (earlier version) · Ahead of 0 of 4 similarly priced models
SWE-bench Verified
Best score per model · Higher is better
#34 of 35
- 77.3%Qwen3.7 MaxSimilar price
- 75.2%Claude Sonnet 4.6Similar price
- 74.2%GLM 5.1Similar price
- 57.9%Qwen3.6 PlusNearby rank
- 57.6%Gemini 2.5 ProSimilar price
- 48.5%GPT-4.1
- 31.0%GPT-4o (2024-11-20)Predecessor
+17.6 pts vs GPT-4o (2024-11-20) (predecessor) · Ahead of 0 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 TextArena #1471415
+79 vs GPT-4o (2024-08-06) (earlier version)
- default141595% CI 1411 to 1418 · 50,235 votes
- Arena VisionArena #851214
+95 vs GPT-4o (2024-08-06) (earlier version)
- default121495% CI 1207 to 1220 · 40,946 votes
- ARC-AGI-2#77 of 850.4%
+0.4 pts vs GPT-4o (2024-11-20) (predecessor)
- default0.4%
- FrontierMath-2025-02-28-Private#40 of 585.5%
+5.2 pts vs GPT-4o (2024-11-20) (predecessor)
- default5.5%
Source:Epoch AI evaluation - FrontierMath-Tier-4-2025-07-01-Private#39 of 460.0%
- default0.0%
Source:Epoch AI evaluation - FrontierMath-Tiers-1-3-v2-Private#85 of 876.0%
+5.6 pts vs GPT-4o (2024-08-06) (earlier version)
- default6.0%
Source:Epoch AI evaluation - GPQA diamond#113 of 16166.9%
+19.0 pts vs GPT-4o (2024-11-20) (predecessor)
- default66.9%
Source:Epoch AI evaluation - Humanity's Last Exam#31 of 345.4%
+2.7 pts vs GPT-4o (2024-11-20) (predecessor)
- default5.4%
- OTIS Mock AIME 2024-2025#124 of 15838.3%
+32.1 pts vs GPT-4o (2024-11-20) (predecessor)
- default38.3%
Source:Epoch AI evaluation - SimpleQA Verified#65 of 8731.1%
+5.1 pts vs GPT-4o (2024-08-06) (earlier version)
- default31.1%
Source:Epoch AI evaluation - SWE-bench Verified#34 of 3548.5%
+17.6 pts vs GPT-4o (2024-11-20) (predecessor)
- default48.5%
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.