AI Benchmark Model

Qwen3 235B A22B 2507 (Reasoning)

Benchmark scores, pricing, speed, and model comparisons for Qwen3 235B A22B 2507 (Reasoning).

Key scores

Intelligence12.7Index score
Coding22.1Index score
Math91.0Index score
Blended Cost$0.75Per 1M tokens

Review benchmark scores, pricing, performance data, and generated comparisons for this AI model.

Benchmark results

12 tracked benchmark rows for Qwen3 235B A22B 2507 (Reasoning).

MATH 500 Math
98.4%
AIME Math
94.0%
AIME 2025 Math
91.0%
MMLU Pro Knowledge
84.3%
GPQA Reasoning
79.0%
LiveCodeBench Code
78.8%
LCR Other
72.0%
TAU2 Other
53.2%
IFBench Other
51.2%
SciCode Other
41.4%
HLE Other
15.9%
TerminalBench Hard Other
13.6%