Qwen3 235B A22B Thinking 2507 — Benchmarks

Benchmark scores for Qwen3 235B A22B Thinking 2507 aggregated from public leaderboards, with how it ranks among open models. See hardware requirements for what you need to run it.

Overall rank: #63 of 123 open modelscomposite 47.1/100 across 7 benchmarks in 4 categories · methodology

Coding

BenchmarkScoreOpen rankAll models
SciCode42.4%#23 / 50#99 / 155

Knowledge

BenchmarkScoreOpen rankAll models
MMLU-Pro84.5%#9 / 119#38 / 259
SimpleQA40.4%#5 / 15#38 / 78

Math

BenchmarkScoreOpen rankAll models
AIME 2024/202586.7%#16 / 74#74 / 270
FrontierMath8.5%#7 / 12#59 / 101

Reasoning

BenchmarkScoreOpen rankAll models
GPQA Diamond80.0%#21 / 83#112 / 291
CritPt0.0%#47 / 50#163 / 167

Scores aggregated from public benchmark sources (each linked from the benchmark pages). llmrun does not run these benchmarks.

Qwen3 235B A22B Thinking 2507 Benchmarks — Scores & Rankings | llmrun