Alibaba (Qwen)
Qwen2.5-32B benchmark results
5 results on 5 benchmarks from 3 sources.
Open weights Released: Sep 17, 2024 Updated Oct 22, 2026
Also listed as: qwen2.5-32b-instruct · Qwen/Qwen2.5-32B-Instruct · Qwen/Qwen2.5-32B
All benchmark results
| Benchmarks | Score | Rank | Setting | Source type | Date |
|---|---|---|---|---|---|
| Open LLM Leaderboard v2 | 46.6% | 22 | Average of 6 normalised benchmarks; bfloat16; 32.764B params“Qwen/Qwen2.5-32B-Instruct” | Official leaderboard | Mar 13, 2025 |
| GPQA Diamond | 46.1% | 223 | Epoch AI run, accuracy | Independent run | Jan 30, 2025 |
| MMLU-Pro | 69.2% | 103 | Overall accuracy; data source: Self-Reported; 32B | Vendor-reported | Mar 11, 2026 |
| AIME (OTIS Mock AIME 2024–2025) | 7.4% | 223 | Epoch AI run, OTIS Mock AIME 2024–2025 | Independent run | Feb 25, 2025 |
| MATH Level 5 | 56.1% | 55 | Epoch AI run, accuracy | Independent run | Jan 30, 2025 |
FAQ
Where do these Qwen2.5-32B scores come from?
From Epoch AI Benchmarking Hub, MMLU-Pro leaderboard (TIGER-Lab), and Hugging Face Open LLM Leaderboard v2 (archived). Each row links to the original leaderboard, dataset or report, and vendor-reported numbers are labelled.