Qwen3 235B A22B Instruct 2507 — Benchmarks

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

Overall rank: #32 of 73 open modelscomposite 50.6/100 across 3 benchmarks in 3 categories · methodology

Coding

BenchmarkScoreOpen rankAll models
Aider Polyglot59.6%#4 / 18#28 / 69

Knowledge

BenchmarkScoreOpen rankAll models
MMLU-Pro83.0%#12 / 119#49 / 259

Reasoning

BenchmarkScoreOpen rankAll models
ARC-AGI11.0%#7 / 10#143 / 158

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