AI Benchmark Model

Qwen3 32B (Reasoning)

Benchmark scores, pricing, speed, and model comparisons for Qwen3 32B (Reasoning).

Key scores

Intelligence8.6Index score
Coding15.3Index score
Math73.0Index score
Blended Cost$0.28Per 1M tokens

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

Benchmark results

12 tracked benchmark rows for Qwen3 32B (Reasoning).

MATH 500 Math
96.1%
AIME Math
80.7%
MMLU Pro Knowledge
79.8%
AIME 2025 Math
73.0%
GPQA Reasoning
66.8%
LiveCodeBench Code
54.6%
IFBench Other
36.3%
SciCode Other
36.0%
TAU2 Other
29.8%
HLE Other
7.4%
TerminalBench Hard Other
3.0%
LCR Other
0.0%