- input
- $2.00
- cached
- $0.50
- output
- $8.00
- Context
- 200Ktokens
- 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 #114
- 1472
Claude Sonnet 5.5Similar price - 1466
Grok 4.5Similar price - 1446
Gemini 2.5 ProSimilar price - 1433
Qwen3.8 27BNearby rank - 1433Gemini 3.1 Flash Lite PreviewNearby rank
- 1432
o3 - 1431Grok 4.1 Fast (Reasoning)Nearby rank
- 1430
MiMo-V2-OmniNearby rank - 1427
Mistral Medium 3.5Similar price
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 #82
- 1280Grok 4.5Similar price
- 1263Claude Sonnet 5.5Similar price
- 1247Gemini 2.5 ProSimilar price
- 1216MiMo-V2-OmniNearby rank
- 1216Qwen3.5-27BNearby rank
- 1216o3
- 1215Gemini 2.5 FlashNearby rank
- 1214Qwen3 VL 235B A22B InstructNearby rank
- 1199Mistral Medium 3.5Similar price
Ahead of 1 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
#59 of 85
- 83.9%Claude Sonnet 5.5Similar price
- 67.1%Grok 4.6Similar price
- 60.4%
Kimi K3Similar price - 9.9%GPT-5Nearby rank
- 8.6%Claude Opus 4Nearby rank
- 6.5%o3
- 5.9%Claude Sonnet 4Nearby rank
- 5.7%GPT-5.4 NanoNearby rank
- 4.9%Gemini 2.5 ProSimilar price
Ahead of 1 of 4 similarly priced models
FrontierMath-2025-02-28-Private
Best score per model · Higher is better
#26 of 58
- 33.4%
GLM 5.1Similar price - 32.4%Claude Sonnet 4.6Similar price
- 21.0%
Qwen3.5 PlusNearby rank - 20.7%Claude Opus 4.5Nearby rank
- 18.7%o3
- 16.4%GLM 5Nearby rank
- 15.2%Claude Sonnet 4.5Nearby rank
- 14.1%Gemini 2.5 ProSimilar price
- 10.3%Gemini 2.5 Pro Preview 06-05Similar price
Ahead of 2 of 4 similarly priced models
FrontierMath-Tier-4-2025-07-01-Private
Best score per model · Higher is better
#32 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
- 2.1%GPT-5 NanoNearby rank
- 2.1%o3
- 2.1%GPT-5.4 MiniNearby rank
- 0.0%Claude Sonnet 3.5 v2Nearby rank
Ahead of 0 of 4 similarly priced models
FrontierMath-Tiers-1-3-v2-Private
Best score per model · Higher is better
#67 of 87
- 88.8%Claude Sonnet 5.5Similar price
- 66.0%Grok 4.6Similar price
- 65.6%Qwen3.8 Max (0902)Similar price
- 34.4%Claude Opus 4.5Nearby rank
- 34.4%Qwen3.7 PlusNearby rank
- 33.3%o3
- 33.3%
InklingNearby rank - 31.2%Qwen3.5 397B A17BNearby rank
- 24.6%Gemini 2.5 ProSimilar price
Ahead of 1 of 4 similarly priced models
GPQA diamond
Best score per model · Higher is better
#85 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
- 82.3%Qwen3.7 FlashNearby rank
- 81.8%Gemini 3.1 Flash LiteNearby rank
- 81.8%o3
- 80.1%Qwen3 235B A22B Thinking 2507Nearby rank
- 79.7%Claude Sonnet 3.7Nearby rank
Ahead of 0 of 4 similarly priced models
Humanity's Last Exam
Best score per model · Higher is better
#18 of 34
- 46.4%Gemini 3.1 Pro PreviewSimilar price
- 46.1%Claude Sonnet 5.5Similar price
- 23.7%GPT-5.1Nearby rank
- 21.6%Gemini 2.5 Pro Preview 06-05Similar price
- 20.3%o3
- 19.4%GPT-5 MiniNearby rank
- 14.2%Claude Opus 4.5Nearby rank
- 7.5%Claude Sonnet 4.5Similar price
Ahead of 1 of 4 similarly priced models
OSWorld
Best score per model · Higher is better
#9 of 10
- 72.1%Claude Sonnet 4.6Similar price
- 62.9%Claude Sonnet 4.5Similar price
- 43.9%Claude Sonnet 4Nearby rank
- 35.8%Claude Sonnet 3.7Nearby rank
- 23.0%o3
- 5.0%Qwen2.5 VL 72B InstructNearby rank
Ahead of 0 of 2 similarly priced models
OTIS Mock AIME 2024-2025
Best score per model · Higher is better
#77 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
- 84.4%GPT-5.5Nearby rank
- 84.4%o3
- 84.4%Qwen3.5-FlashNearby rank
- 84.4%Qwen3.6 FlashNearby rank
Ahead of 0 of 4 similarly priced models
SimpleQA Verified
Best score per model · Higher is better
#31 of 87
- 66.2%Gemini 3.5 FlashSimilar price
- 56.0%Grok 4.7Similar price
- 50.6%Kimi K3Nearby rank
- 50.1%GPT-5Nearby rank
- 49.4%o3
- 49.3%Grok 4.6Nearby rank
- 48.7%Qwen3 MaxNearby rank
- 47.3%Qwen3.8 Max (0902)Similar price
- 46.5%Claude Sonnet 5.5Similar price
Ahead of 2 of 4 similarly priced models
SWE-bench Verified
Best score per model · Higher is better
#30 of 35
- 77.3%Qwen3.7 MaxSimilar price
- 75.2%Claude Sonnet 4.6Similar price
- 74.2%GLM 5.1Similar price
- 65.9%GPT-5.1Nearby rank
- 64.7%GPT-5 MiniNearby rank
- 62.3%o3
- 61.0%Claude Sonnet 3.7Nearby rank
- 57.9%Qwen3.6 PlusNearby rank
- 57.6%Gemini 2.5 ProSimilar price
Ahead of 1 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.
Reasoning effort
ARC-AGI-2
Score by reasoning effort · Higher is better
FrontierMath-2025-02-28-Private
Score by reasoning effort · Higher is better
FrontierMath-Tiers-1-3-v2-Private
Score by reasoning effort · Higher is better
GPQA diamond
Score by reasoning effort · Higher is better
Humanity's Last Exam
Score by reasoning effort · Higher is better
OTIS Mock AIME 2024-2025
Score by reasoning effort · Higher is better
All published scores
- Arena TextArena #1141432
- default143295% CI 1428 to 1435 · 58,811 votes
- Arena VisionArena #821216
- default121695% CI 1209 to 1222 · 45,507 votes
- ARC-AGI-2#59 of 856.5%
- low2.0%
- medium3.0%
- high6.5%
- FrontierMath-2025-02-28-Private#26 of 5818.7%
- low9.7%
- medium16.9%
- high18.7%
Source:Epoch AI evaluation - FrontierMath-Tier-4-2025-07-01-Private#32 of 462.1%
- high2.1%
Source:Epoch AI evaluation - FrontierMath-Tiers-1-3-v2-Private#67 of 8733.3%
- low19.3%
- medium29.8%
- high33.3%
Source:Epoch AI evaluation - GPQA diamond#85 of 16181.8%
- low79.8%
- medium80.8%
- high81.8%
Source:Epoch AI evaluation - Humanity's Last Exam#18 of 3420.3%
- medium19.2%
- high20.3%
- OSWorld#9 of 1023.0%
- medium23.0%o3 (100 steps)
- medium17.2%o3 (50 steps)
- medium9.1%o3 (15 steps)
- OTIS Mock AIME 2024-2025#77 of 15884.4%
- low60.0%
- medium84.4%
- high83.9%
Source:Epoch AI evaluation - SimpleQA Verified#31 of 8749.4%
- high49.4%
Source:Epoch AI evaluation - SWE-bench Verified#30 of 3562.3%
- medium62.3%
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.