- Context
- 128Ktokens
- Released
- 2y ago
- Size
- 90Bparameters
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 Vision
Best Arena rating per model · Higher is better
Arena #148
- 1161
Claude Sonnet 3.5 v2Similar release date - 1118
GPT-4o (2024-08-06)Similar release date - 1089GPT-4.1 NanoNearby rank
- 1045
Molmo 72BSimilar release date - 1032
Llama-3.2-90B-Vision-Instruct - 1025
Pixtral 12BSimilar release date - 1019
Nova Lite 1.0Nearby rank
Ahead of 0 of 4 models released around the same time
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
#147 of 161
- 55.3%Claude Sonnet 3.5 v2Similar release date
- 49.2%GPT-4o (2024-08-06)Similar release date
- 49.1%
Qwen2.5 72B InstructSimilar release date - 44.2%Llama 3.1 70B InstructNearby rank
- 41.8%
Qwen TurboNearby rank - 41.0%Llama-3.2-90B-Vision-Instruct
- 39.5%
Gemma 3 12BNearby rank - 38.1%Claude Haiku 3.5Nearby rank
- 35.5%Qwen2.5 7B InstructSimilar release date
Ahead of 1 of 4 models released around the same time
OTIS Mock AIME 2024-2025
Best score per model · Higher is better
#151 of 158
- 8.5%Claude Sonnet 3.5 v2Similar release date
- 8.1%Qwen2.5 72B InstructSimilar release date
- 6.4%GPT-4o (2024-08-06)Similar release date
- 4.3%Claude Haiku 3.5Nearby rank
- 3.6%Llama 3.1 70B InstructNearby rank
- 2.6%Llama-3.2-90B-Vision-Instruct
- 2.5%Qwen2.5 7B InstructSimilar release date
- 1.8%Claude Haiku 3Nearby 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
- Arena VisionArena #1481032
- default103295% CI 1023 to 1042 · 8,682 votes
- GPQA diamond#147 of 16141.0%
- default41.0%
Source:Epoch AI evaluation - OTIS Mock AIME 2024-2025#151 of 1582.6%
- default2.6%
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.