Up to four models
Qwen3-32B vs Qwen2.5-32B
On the index (GPT-4 = 100), Qwen3-32B scores 129 and Qwen2.5-32B 111. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.
129113–145
WeightsOpen
ReleasedApr 2025
Price in / out$0.080 / $0.28
Context131K
Core tests taken1 of 9
Qwen3-32B leads Qwen2.5-32B by 18 points, ahead on 1 of 1 shared core tests.
Test by testthird-party results
Every result as a table
| Test | Qwen3-32B | Qwen2.5-32B |
|---|---|---|
| Reasoning & knowledge | ||
| GPQA Diamond (Epoch AI) | 65.7% | 46.1% |
| Maths | ||
| AIME-style maths (OTIS mock) | 66.9% | 7.4% |
Tests at least two of these models have taken. Bold rows are the core tests.