TPSTokens Per Second

QwQ-32B

Alibaba / Qwen🇨🇳 China
active

Open reasoning model matching o1-mini on math and coding. Apache 2.0 licensed.

Compare with other models →
Context window131K tokens
Input / 1M tokens$0.15
Output / 1M tokens$0.6

Version History

QwQ-32Bmajor

QwQ-32B is Alibaba's open reasoning model rivaling o1-mini on AIME and MATH. Apache 2.0, runs on a single A100.

Benchmark Scores

Full leaderboard →
79.5%
AIME 2024
80.3%
AIME 2025
71.5%
GPQA
90.2%
HumanEval
68.3%
LiveCodeBench
94.5%
MATH
85.4%
MMLU
72.4%
MMLU-Pro
50.0 tokens_per_sec
Speed (tok/s)