- Context
- 33Ktokens
- Released
- 2y ago
- Size
- 46.7Bparameters
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 #354
- 1346
GPT-4o (2024-05-13)Similar release date - 1346
Qwen-PlusSimilar release date - 1262
Claude Haiku 3Similar release date - 1211
Llama 3.1 8B InstructNearby rank - 1200
Gemma 2 2B ITNearby rank - 1197
Mixtral 8x7B Instruct v0.1 - 1167Llama 3.2 3B InstructNearby rank
- 1153
SOLAR 10.7B Instruct v1.0Similar release date
Ahead of 1 of 4 models released around the same time
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
#155 of 161
- 56.1%
Qwen MaxSimilar release date - 48.9%GPT-4o (2024-05-13)Similar release date
- 48.1%Qwen-PlusSimilar release date
- 36.3%Claude Haiku 3Similar release date
- 35.5%Qwen2.5 7B InstructNearby rank
- 30.6%Mixtral 8x7B Instruct v0.1
- 27.0%Llama 3.1 8B InstructNearby rank
- 23.9%Llama 3.2 1B InstructNearby 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
- Arena TextArena #3541197
- default119795% CI 1193 to 1202 · 73,503 votes
- GPQA diamond#155 of 16130.6%
- default30.6%
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.