Up to four models
QwQ-32B vs Qwen3-8B On the index (GPT-4 = 100), QwQ-32B scores 127 and Qwen3-8B 126. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.
Next to QwQ-32B Cheapest at this level gpt-oss-20b Best closed model GPT-6.2 Closest rival, another lab DeepSeek-R1-Distill-Qwen-32B The version it replaced QwQ-32B-Preview Where it started GPT-4 Presets Best open vs best closed (measured) Today vs GPT-4 (2023) Top three labs US vs China, best of each
QwQ-32B 127 111–142
Weights Open
Released Mar 2025
Price in / out –
Context –
Core tests taken 1 of 9
Qwen3-8B 126 110–141
Weights Open
Released Apr 2025
Price in / out –
Context –
Core tests taken 1 of 9
QwQ-32B and Qwen3-8B are too close to call (1 point apart, within the uncertainty), ahead on 1 of 1 shared core tests.
Test by testthird-party results QwQ-32B Qwen3-8B0% 25% 50% 75% 100% REASONING & KNOWLEDGE GPQA Diamond (Epoch AI)GPQA Diamond (Epoch AI) Fiction.LiveBenchFiction.LiveBench MATHS AIME-style maths (OTIS mock)AIME-style maths (OTIS mock) Every result as a table Tests at least two of these models have taken. Bold rows are the core tests.
Compare QwQ-32B with Close on score DeepSeek-R1-Distill-Qwen-32B Close on score Qwen3-30B-A3B-Instruct (Jul 2025) Earlier Alibaba model QwQ-32B-Preview