- input
- $0.45
- output
- $3.50
- Context
- 128Ktokens
- Released
- 1y ago
- Size
- 235Bparameters
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 #168
- 1464
DeepSeek V4 Pro 0813Similar price - 1461
Kimi K2.6Similar price - 1426
Nemotron 3 UltraSimilar price - 1402
Claude Sonnet 4Nearby rank - 1401
GPT-5.4 NanoNearby rank - 1400
Qwen3 235B A22B Thinking 2507 - 1399Qwen3 Next 80B A3B InstructNearby rank
- 1396Qwen3.5-FlashNearby rank
- 1290
Nova Pro 1.0Similar price
Ahead of 1 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
FrontierMath-2025-02-28-Private
Best score per model · Higher is better
#33 of 58
- 39.0%Kimi K2.6Similar price
- 35.6%
Gemini 3 Flash PreviewSimilar price - 28.3%GPT-5.4 MiniSimilar price
- 10.3%Gemini 2.5 Pro Preview 06-05Nearby rank
- 10.3%Qwen3.6 FlashNearby rank
- 8.5%Qwen3 235B A22B Thinking 2507
- 8.3%GPT-5 NanoNearby rank
- 7.2%Claude Opus 4.1Nearby rank
- 2.4%
GLM 4.7Similar price
Ahead of 1 of 4 similarly priced models
FrontierMath-Tier-4-2025-07-01-Private
Best score per model · Higher is better
#39 of 46
- 14.6%Kimi K2.6Similar price
- 4.2%Gemini 3 Flash PreviewSimilar price
- 2.1%GPT-5.4 MiniSimilar price
- 0.0%Kimi K2 ThinkingNearby rank
- 0.0%GPT-4.1Nearby rank
- 0.0%Qwen3 235B A22B Thinking 2507
- 0.0%Qwen3.5-FlashNearby rank
- 0.0%Qwen3.6 FlashNearby rank
- 0.0%GLM 4.7Similar price
Ahead of 0 of 4 similarly priced models
GPQA diamond
Best score per model · Higher is better
#87 of 161
- 91.7%DeepSeek V4 Pro 0813Similar price
- 89.4%Gemini 3 Flash PreviewSimilar price
- 88.1%
Mistral Large 4Similar price - 87.9%Kimi K2.7 CodeSimilar price
- 81.8%Gemini 3.1 Flash LiteNearby rank
- 81.8%o3Nearby rank
- 80.1%Qwen3 235B A22B Thinking 2507
- 79.7%Claude Sonnet 3.7Nearby rank
- 79.2%Claude Sonnet 4Nearby rank
Ahead of 0 of 4 similarly priced models
OTIS Mock AIME 2024-2025
Best score per model · Higher is better
#66 of 158
- 98.6%DeepSeek V4 Pro 0813Similar price
- 98.3%Mistral Large 4Similar price
- 95.6%Gemini 3 Flash PreviewSimilar price
- 95.6%Kimi K2.7 CodeSimilar price
- 86.7%Nemotron 3 UltraNearby rank
- 86.7%GPT-5 MiniNearby rank
- 86.7%Qwen3 235B A22B Thinking 2507
- 86.7%Qwen3.6 35B A3BNearby rank
- 86.7%Qwen3.7 FlashNearby rank
Ahead of 0 of 4 similarly priced models
SimpleQA Verified
Best score per model · Higher is better
#52 of 87
- 66.8%Gemini 3 Flash PreviewSimilar price
- 52.9%DeepSeek V4 Pro 0813Similar price
- 41.0%GPT-5.6 LunaNearby rank
- 41.0%GLM 5.3Nearby rank
- 40.4%Qwen3 235B A22B Thinking 2507
- 40.3%
InklingNearby rank - 37.1%GPT-5.2Nearby rank
- 36.5%Kimi K2.7 CodeSimilar price
- 20.0%Mistral Large 4Similar 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 #1681400
- default140095% CI 1394 to 1407 · 8,812 votes
- FrontierMath-2025-02-28-Private#33 of 588.5%
- default8.5%
Source:Epoch AI evaluation - FrontierMath-Tier-4-2025-07-01-Private#39 of 460.0%
- default0.0%
Source:Epoch AI evaluation - GPQA diamond#87 of 16180.1%
- default80.1%
Source:Epoch AI evaluation - OTIS Mock AIME 2024-2025#66 of 15886.7%
- default86.7%
Source:Epoch AI evaluation - SimpleQA Verified#52 of 8740.4%
- default40.4%
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.