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: #14 of 73 open modelscomposite 62.5/100 across 5 benchmarks in 3 categories · methodology

Knowledge

BenchmarkScoreOpen rankAll models
MMLU-Pro84.5%#9 / 119#38 / 259
SimpleQA50.1%#2 / 11#19 / 65

Math

BenchmarkScoreOpen rankAll models
AIME 2024/202586.7%#7 / 34#41 / 155
FrontierMath8.5%#7 / 12#59 / 101

Reasoning

BenchmarkScoreOpen rankAll models
GPQA Diamond80.0%#9 / 46#59 / 182

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