- Context
- 131Ktokens
- Released
- 1y ago
- Size
- 32Bparameters
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 #246
- 1365
Gemma 3 27BSimilar release date - 1354
Command ASimilar release date - 1338
GPT-5 NanoNearby rank - 1336GPT-4o (2024-08-06)Nearby rank
- 1336
QwQ 32B - 1335
Nova 2 LiteNearby rank - 1329
Olmo 3.1 32B InstructNearby rank - 1328
Llama 3.3 Nemotron Super 49B v1Similar release date - 1303
Mistral Small 3.1 24BSimilar 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
#117 of 161
- 79.7%
Claude Sonnet 3.7Similar release date - 67.6%
DeepSeek V3 0324Similar release date - 65.7%
Qwen3 32BNearby rank - 65.4%QwQ PlusNearby rank
- 65.3%QwQ 32B
- 64.1%DeepSeek-R1-Distill-Qwen-32BNearby rank
- 63.8%Qwen3 14BNearby rank
- 51.8%
Llama 4 ScoutSimilar release date - 47.7%Gemma 3 27BSimilar release date
Ahead of 2 of 4 models released around the same time
OTIS Mock AIME 2024-2025
Best score per model · Higher is better
#113 of 158
- 62.2%Qwen3 30B A3B Instruct 2507Nearby rank
- 61.7%Qwen3.5-9BNearby rank
- 59.2%QwQ 32B
- 58.3%
GLM 4.7 FlashNearby rank - 57.8%Claude Sonnet 3.7Similar release date
- 37.8%DeepSeek V3 0324Similar release date
- 22.5%Gemma 3 27BSimilar release date
- 7.8%Llama 4 ScoutSimilar release date
Ahead of 4 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 #2461336
- default133695% CI 1331 to 1340 · 25,166 votes
- GPQA diamond#117 of 16165.3%
- default65.3%
Source:Epoch AI evaluation - OTIS Mock AIME 2024-2025#113 of 15859.2%
- default59.2%
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.