- Context
- 1Mtokens
- Released
- 2y 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
Not ranked on Arena Text yet
Arena WebDev
Best Arena rating per model · Higher is better
Not ranked on Arena WebDev yet
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
GPQA diamond
Best score per model · Higher is better
#146 of 161
- 55.3%
Claude Sonnet 3.5 v2Similar release date - 51.3%
Mistral Large 2.1Similar release date - 47.9%
GPT-4o (2024-11-20)Similar release date - 47.4%
Llama 3.3 70B InstructSimilar release date - 44.2%Llama 3.1 70B InstructNearby rank
- 41.8%
Qwen Turbo - 41.0%Llama-3.2-90B-Vision-InstructNearby rank
- 39.5%
Gemma 3 12BNearby rank
Ahead of 0 of 4 models released around the same time
OTIS Mock AIME 2024-2025
Best score per model · Higher is better
#146 of 158
- 8.5%Claude Sonnet 3.5 v2Similar release date
- 7.8%Mistral Large 2.1Similar release date
- 6.3%GPT-4o (2024-05-13)Nearby rank
- 6.3%GPT-4o (2024-11-20)Similar release date
- 6.1%Qwen Turbo
- 5.1%Llama 3.3 70B InstructSimilar release date
- 4.3%Claude Haiku 3.5Nearby rank
Ahead of 1 of 4 models released around the same time
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
- GPQA diamond#146 of 16141.8%
- default41.8%
Source:Epoch AI evaluation - OTIS Mock AIME 2024-2025#146 of 1586.1%
- default6.1%
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.