- Context
- 1Mtokens
- Released
- 11mo ago
- Size
- —parameters
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 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
#76 of 161
- 92.6%
Gemini 3 Pro PreviewSimilar release date - 91.4%
GPT-5.2Similar release date - 86.0%
Claude Opus 4.5Similar release date - 84.2%
Kimi K2 Thinking TurboNearby rank - 83.5%
Qwen3.5-35B-A3BNearby rank - 83.4%
DeepSeek Reasoner - 83.3%Gemini 3.5 Flash LiteNearby rank
- 83.3%Qwen3.6 FlashNearby rank
- 83.3%
GLM 4.7Similar release date
Ahead of 1 of 4 models released around the same time
OTIS Mock AIME 2024-2025
Best score per model · Higher is better
#64 of 158
- 96.1%GPT-5.2Similar release date
- 91.4%Gemini 3 Pro PreviewSimilar release date
- 88.9%
InklingNearby rank - 88.6%GPT-5.1Nearby rank
- 87.8%DeepSeek Reasoner
- 87.8%GPT-5.4 NanoNearby rank
- 86.7%
Qwen3.5 PlusNearby rank - 86.1%Claude Opus 4.5Similar release date
- 83.3%GLM 4.7Similar release date
Ahead of 2 of 4 models released around the same time
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
- GPQA diamond#76 of 16183.4%
- default83.4%
Source:Epoch AI evaluation - OTIS Mock AIME 2024-2025#64 of 15887.8%
- default87.8%
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.