- Context
- 131Ktokens
- Released
- 1y ago
- Size
- 23.6Bparameters
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
ARC-AGI-2
Best score per model · Higher is better
#78 of 85
- 8.6%
Claude Opus 4Similar release date - 4.9%
o3 ProSimilar release date - 1.1%
R1 0528Similar release date - 0.0%
Gemini 2.5 Pro Preview 06-05Similar release date - 0.0%
Llama 4 MaverickNearby rank - 0.0%Llama 4 ScoutNearby rank
- 0.0%
Magistral Small - 0.0%GPT-4.1 MiniNearby rank
- 0.0%GPT-4.1 NanoNearby rank
Ahead of 0 of 4 models released around the same time
GPQA diamond
Best score per model · Higher is better
#128 of 161
- 84.8%Gemini 2.5 Pro Preview 06-05Similar release date
- 79.2%Claude Sonnet 4Similar release date
- 63.8%
Qwen3 14BSimilar release date - 56.1%
Qwen MaxNearby rank - 56.1%
Phi 4Nearby rank - 56.1%Magistral Small
- 55.6%Qwen3 30B A3B Instruct 2507Nearby rank
- 55.3%Claude Sonnet 3.5 v2Nearby rank
- 9.3%DeepSeek R1 0528 Qwen3 8BSimilar 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
#128 of 158
- 84.7%Gemini 2.5 ProSimilar release date
- 71.1%Claude Sonnet 4Similar release date
- 66.4%Qwen3 14BSimilar release date
- 43.9%DeepSeek R1 0528 Qwen3 8BSimilar release date
- 37.8%DeepSeek V3 0324Nearby rank
- 32.2%Mistral Medium 3Nearby rank
- 30.0%Magistral Small
- 28.9%GPT-4.1 NanoNearby rank
- 28.1%Magistral Small 1.2Nearby rank
Ahead of 0 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
- ARC-AGI-2#78 of 850.0%
- default0.0%
- GPQA diamond#128 of 16156.1%
- default56.1%
Source:Epoch AI evaluation - OTIS Mock AIME 2024-2025#128 of 15830.0%
- default30.0%
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.