- input
- $0.05
- output
- $0.10
- Context
- 131Ktokens
- Released
- 1y ago
- Size
- 4Bparameters
Cost/1M tokens
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 #289
- 1318
gpt-oss-20bSimilar price - 1306
Olmo 3 32B ThinkNearby rank - 1306
Mistral Large 2.1Nearby rank - 1303
Gemma 3 4B - 1303
Qwen2.5 72B InstructNearby rank - 1303Mistral Small 3.1 24BNearby rank
- 1274Mistral Small 3Similar price
- 1241
Nova Micro 1.0Similar price - 1200Gemma 2 2B ITPredecessor
- 1111
Llama 3.2 1B InstructSimilar price
+103 vs Gemma 2 2B IT (predecessor) · Ahead of 3 of 4 similarly priced models
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
Not ranked on Arena Vision 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
#159 of 161
- 90.2%
GLM 5.3 FlashSimilar price - 82.3%Qwen3.7 FlashSimilar price
- 60.8%gpt-oss-20bSimilar price
- 27.0%Llama 3.1 8B InstructNearby rank
- 23.9%Llama 3.2 1B InstructSimilar price
- 23.2%Gemma 3 4B
- 15.2%Mistral 7B Instruct v0.3Nearby rank
- 9.3%
DeepSeek R1 0528 Qwen3 8BNearby rank
Ahead of 0 of 4 similarly priced models
OTIS Mock AIME 2024-2025
Best score per model · Higher is better
#141 of 158
- 93.9%GLM 5.3 FlashSimilar price
- 86.7%Qwen3.7 FlashSimilar price
- 65.3%gpt-oss-20bSimilar price
- 7.8%Llama 4 ScoutNearby rank
- 7.8%Mistral Large 2.1Nearby rank
- 7.5%Gemma 3 4B
- 6.9%GPT-4o-mini (2024-07-18)Nearby rank
- 6.4%GPT-4o (2024-08-06)Nearby rank
- 0.6%Llama 3.2 1B InstructSimilar price
Ahead of 1 of 4 similarly priced models
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 #2891303
+103 vs Gemma 2 2B IT (predecessor)
- default130395% CI 1294 to 1313 · 4,171 votes
- GPQA diamond#159 of 16123.2%
- default23.2%
Source:Epoch AI evaluation - OTIS Mock AIME 2024-2025#141 of 1587.5%
- default7.5%
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.