- input
- $0.0605
- output
- $0.40
- Context
- 200Ktokens
- Released
- 9mo ago
- Size
- 31.2Bparameters
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 #206
- 1454
Hy3Similar price - 1393
Step 3.5 FlashSimilar price - 1382
Qwen3 30B A3B Instruct 2507Similar price - 1369
Qwen3-Next 80B-A3B (Thinking)Nearby rank - 1365
Gemma 3 27BSimilar price - 1364
GLM 4.7 Flash - 1360Gemini 2.0 FlashNearby rank
- 1360
Nemotron 3 SuperNearby rank
Ahead of 0 of 4 similarly priced models
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
#122 of 161
- 69.4%
GPT-5 NanoSimilar price - 63.8%Qwen3 14BSimilar price
- 61.7%Qwen3 30B A3BNearby rank
- 60.8%gpt-oss-20bNearby rank
- 60.5%GLM 4.7 Flash
- 59.5%
Mistral Medium 3Nearby rank - 56.8%Qwen3 8BNearby rank
- 51.8%
Llama 4 ScoutSimilar price - 47.7%Gemma 3 27BSimilar price
Ahead of 2 of 4 similarly priced models
OTIS Mock AIME 2024-2025
Best score per model · Higher is better
#114 of 158
- 81.1%GPT-5 NanoSimilar price
- 66.4%Qwen3 14BSimilar price
- 61.7%Qwen3.5-9BNearby rank
- 59.2%QwQ 32BNearby rank
- 58.3%GLM 4.7 Flash
- 57.8%
Claude Sonnet 3.7Nearby rank - 56.1%Qwen3 8BNearby rank
- 22.5%Gemma 3 27BSimilar price
- 7.8%Llama 4 ScoutSimilar price
Ahead of 2 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 #2061364
- default136495% CI 1359 to 1370 · 11,937 votes
- GPQA diamond#122 of 16160.5%
- none45.1%
- default60.5%
Source:Epoch AI evaluation - OTIS Mock AIME 2024-2025#114 of 15858.3%
- none25.0%
- default58.3%
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.