Limited access
Opens to everyone soon · Announcement
- Context
- 1Mtokens
- Released
- 2w 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 #1
- 1526
Gemini 4 Carbon - 1522Gemini 4 ArgonNearby rank
- 1511
Muse WonderNearby rank - 1487
Kimi K3Similar price - 1482
GPT-6.1 SolSimilar price - 1472
Claude Sonnet 5.5Similar price - 1354
Command ASimilar price
Ahead of 4 of 4 similarly priced models
Arena WebDev
Best Arena rating per model · Higher is better
Arena #4
- 1814Claude Opus 5.5Nearby rank
- 1773Claude Sonnet 5.5Similar price
- 1768Gemini 4 Carbon
- 1764GPT-6 AstraNearby rank
- 1743GPT-6.1 SolSimilar price
- 1676
Qwen3.8 Max (0902)Similar price - 1658Kimi K3Similar price
Ahead of 2 of 4 similarly priced models
Arena Vision
Best Arena rating per model · Higher is better
Not ranked on Arena Vision yet
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
Arena #3
- +0.304Claude Fable 5.2Nearby rank
- +0.195Claude Opus 5.5Nearby rank
- +0.170Gemini 4 Carbon
- +0.160Claude Sonnet 5.5Similar price
- +0.148Claude Fable 5.1Nearby rank
- +0.125GPT-6.1 SolSimilar price
- +0.026
Grok 4.7Similar price - +0.006Kimi K3Similar price
Ahead of 3 of 4 similarly priced models
ARC-AGI-2
Best score per model · Higher is better
#2 of 85
- 95.0%GPT-6 AstraNearby rank
- 94.2%Gemini 4 Carbon
- 94.2%GPT-6.1 SolSimilar price
- 93.8%Claude Fable 5.2Nearby rank
- 83.9%Claude Sonnet 5.5Similar price
- 67.1%Grok 4.6Similar price
- 60.4%Kimi K3Similar price
Ahead of 3 of 4 similarly priced models
FrontierMath-Tier-4-v2-Private
Best score per model · Higher is better
#4 of 72
- 100.0%GPT-6.1 SolSimilar price
- 97.6%GPT-6 AstraNearby rank
- 95.1%Gemini 4 Carbon
- 95.0%Claude Opus 5.5Nearby rank
- 92.7%GPT-6.1 TerraNearby rank
- 80.5%Claude Sonnet 5.5Similar price
- 39.0%Kimi K3Similar price
- 34.1%Qwen3.8 Max (0902)Similar price
Ahead of 3 of 4 similarly priced models
FrontierMath-Tiers-1-3-v2-Private
Best score per model · Higher is better
#6 of 87
- 93.7%GPT-6.1 SolSimilar price
- 91.2%Claude Opus 5.5Nearby rank
- 90.9%GPT-6.1 TerraNearby rank
- 90.5%Gemini 4 Carbon
- 90.2%Claude Fable 5.1Nearby rank
- 89.8%GPT-6 SolNearby rank
- 88.8%Claude Sonnet 5.5Similar price
- 72.2%Kimi K3Similar price
- 66.0%Grok 4.6Similar price
Ahead of 3 of 4 similarly priced models
GPQA diamond
Best score per model · Higher is better
#1 of 161
- 96.5%Gemini 4 Carbon
- 96.4%Gemini 4 ArgonNearby rank
- 95.8%GPT-6 AstraNearby rank
- 95.6%Claude Sonnet 5.5Similar price
- 95.4%GPT-6.1 SolSimilar price
- 94.0%Grok 4.6Similar price
- 93.1%Kimi K3Similar price
Ahead of 4 of 4 similarly priced models
OTIS Mock AIME 2024-2025
Best score per model · Higher is better
#1 of 158
- 100.0%Claude Sonnet 5.5Similar price
- 100.0%Gemini 4 ArgonNearby rank
- 100.0%Gemini 4 Carbon
- 100.0%GPT-5.6 SolNearby rank
- 100.0%GPT-6 AstraNearby rank
- 100.0%GPT-6 SolSimilar price
- 100.0%Qwen3.8 Max (0902)Similar price
- 97.2%Kimi K3Similar price
Ahead of 1 of 4 similarly priced models
SimpleQA Verified
Best score per model · Higher is better
#2 of 87
- 94.0%Claude Fable 5.2Nearby rank
- 77.7%Gemini 4 Carbon
- 76.0%Gemini 4 ArgonNearby rank
- 75.6%GPT-6 AstraNearby rank
- 73.9%GPT-6.1 SolSimilar price
- 56.0%Grok 4.7Similar price
- 50.6%Kimi K3Similar price
- 46.5%Claude Sonnet 5.5Similar price
Ahead of 4 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
All published scores
- Arena TextArena #11526
- high152695% CI 1516 to 1536 · 4,282 votes
- Arena WebDevArena #41768
- high176895% CI 1753 to 1783 · 2,120 votes
- Agent ArenaArena #3+0.170
- high+0.17095% CI +0.163 to +0.177 · 9,558,978 observations
- ARC-AGI-2#2 of 8594.2%
- low49.6%
- medium94.2%
- high92.1%
- FrontierMath-Tier-4-v2-Private#4 of 7295.1%
- high95.1%
Source:Epoch AI evaluation - FrontierMath-Tiers-1-3-v2-Private#6 of 8790.5%
- high90.5%
Source:Epoch AI evaluation - GPQA diamond#1 of 16196.5%
- high96.5%
Source:Epoch AI evaluation - OTIS Mock AIME 2024-2025#1 of 158100.0%
- high100.0%
Source:Epoch AI evaluation - SimpleQA Verified#2 of 8777.7%
- high77.7%
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.