- input
- $0.10
- cached
- $0.025
- output
- $0.90
- Context
- 262Ktokens
- Released
- 6mo ago
- Size
- 35Bparameters
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
Not ranked on Arena Text yet
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
FrontierMath-Tiers-1-3-v2-Private
Best score per model · Higher is better
#77 of 87
- 75.1%
Claude Haiku 5.5Similar price - 71.2%
DeepSeek V4.1 Flash 1017Similar price - 68.8%
GLM 5.3Similar price - 23.9%Claude Sonnet 4.5Nearby rank
- 22.5%
Qwen3.6 FlashNearby rank - 20.4%Qwen3.6 35B A3B
- 20.0%
GPT-5 NanoNearby rank - 19.3%Qwen3.7 FlashNearby rank
- 0.7%GPT-4o-mini (2024-07-18)Similar price
Ahead of 1 of 4 similarly priced models
GPQA diamond
Best score per model · Higher is better
#71 of 161
- 93.2%DeepSeek V4.1 Flash 1017Similar price
- 90.9%GLM 5.3Similar price
- 84.8%
Qwen3.5 PlusNearby rank - 84.8%
Gemini 2.5 Pro Preview 06-05Nearby rank - 84.8%Qwen3.6 35B A3B
- 84.2%
Kimi K2 Thinking TurboNearby rank - 83.5%Qwen3.5-35B-A3BPredecessor
- 75.8%Gemma 4 31BSimilar price
- 75.8%gpt-oss-120bSimilar price
+1.4 pts vs Qwen3.5-35B-A3B (predecessor) · Ahead of 2 of 4 similarly priced models
OTIS Mock AIME 2024-2025
Best score per model · Higher is better
#66 of 158
- 99.4%DeepSeek V4.1 Flash 1017Similar price
- 91.1%GLM 5.3Similar price
- 88.9%gpt-oss-120bSimilar price
- 86.7%GPT-5 MiniNearby rank
- 86.7%Qwen3 235B A22B Thinking 2507Nearby rank
- 86.7%Qwen3.6 35B A3B
- 86.7%Qwen3.7 FlashNearby rank
- 86.4%GLM 5.2Nearby rank
- 73.3%Gemma 4 31BSimilar price
- 70.0%Qwen3.5-35B-A3BPredecessor
+16.7 pts vs Qwen3.5-35B-A3B (predecessor) · Ahead of 1 of 4 similarly priced models
Terminal Bench
Best score per model · Higher is better
#43 of 49
- 45.1%
MiniMax M2.7Similar price - 42.7%MiniMax M2.5Similar price
- 39.6%DeepSeek V3.2Similar price
- 27.8%Kimi K2 InstructNearby rank
- 25.8%
x-AI/Grok-Code-Fast 1Nearby rank - 24.6%Qwen3.6 35B A3B
- 24.5%GLM 4.6Nearby rank
- 21.8%GPT-5 NanoNearby rank
- 18.7%gpt-oss-120bSimilar 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
- FrontierMath-Tiers-1-3-v2-Private#77 of 8720.4%
- none20.4%
- default17.5%
Source:Epoch AI evaluation - GPQA diamond#71 of 16184.8%
+1.4 pts vs Qwen3.5-35B-A3B (predecessor)
- none84.8%
- default83.8%
Source:Epoch AI evaluation - OTIS Mock AIME 2024-2025#66 of 15886.7%
+16.7 pts vs Qwen3.5-35B-A3B (predecessor)
- none68.9%
- default86.7%
Source:Epoch AI evaluation - Terminal Bench#43 of 4924.6%
- default24.6%little-coder
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.