- input
- $0.60
- cached
- $0.12
- output
- $2.40
- Context
- 262Ktokens
- Released
- 5mo ago
- Size
- 550Bparameters
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 #122
- 1458
DeepSeek V4 Pro 0423Similar price - 1450
Kimi K2.5Similar price - 1441
GLM 4.7Similar price - 1430Kimi K2 Thinking TurboNearby rank
- 1427
Mistral Medium 3.5Nearby rank - 1426
Nemotron 3 Ultra - 1426
Claude Opus 4Nearby rank - 1425DeepSeek V3.2 ExpNearby rank
- 1423Mistral Large 4Similar price
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
Arena #55
- +0.005
Hy4 previewSimilar price - -0.022
Gemini 3.7 FlashSimilar price - -0.037
Step 5 PreviewSimilar price - -0.054Mistral Large 4Similar price
- -0.105
MiniMax M3Nearby rank - -0.137Mistral Medium 3.5Nearby rank
- -0.156Nemotron 3 Ultra
- -0.173
InklingNearby rank - -0.181Inkling SmallNearby rank
Ahead of 0 of 4 similarly priced models
GPQA diamond
Best score per model · Higher is better
#69 of 161
- 90.9%DeepSeek V4 Pro 0423Similar price
- 88.1%Mistral Large 4Similar price
- 85.9%Claude Fable 5Nearby rank
- 85.9%
Qwen3.6 27BSimilar price - 85.4%Nemotron 3 Ultra
- 85.3%Gemini 2.5 ProNearby rank
- 84.8%
Qwen3.5 PlusNearby rank - 83.3%GLM 4.7Similar price
Ahead of 1 of 4 similarly priced models
OTIS Mock AIME 2024-2025
Best score per model · Higher is better
#66 of 158
- 98.3%Mistral Large 4Similar price
- 96.7%DeepSeek V4 Pro 0423Similar price
- 91.1%Qwen3.6 27BSimilar price
- 87.8%
GPT-5.4 NanoNearby rank - 86.7%Qwen3.5 PlusNearby rank
- 86.7%Nemotron 3 Ultra
- 86.7%GPT-5 MiniNearby rank
- 86.7%Qwen3 235B A22B Thinking 2507Nearby rank
- 83.3%GLM 4.7Similar 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 #1221426
- default1426NVFP495% CI 1420 to 1433 · 11,399 votes
- Agent ArenaArena #55-0.156
- default-0.15695% CI -0.189 to -0.123 · 239,778 observations
- GPQA diamond#69 of 16185.4%
- default85.4%
Source:Epoch AI evaluation - OTIS Mock AIME 2024-2025#66 of 15886.7%
- default86.7%
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.