Alibaba (Qwen)
Qwen2.5-Max benchmark results
5 results on 5 benchmarks from 3 sources.
Closed Released: Jan 25, 2025 Updated Oct 22, 2026
Also listed as: qwen2.5-max · qwen-max-2025-01-25
All benchmark results
| Benchmarks | Score | Rank | Setting | Source type | Date |
|---|---|---|---|---|---|
| LMArena Text | 1374 | 193 | Overall, style control on; 32489 votes; 95% CI 1370–1378“qwen2.5-max” | Official leaderboard | Oct 8, 2026 |
| GPQA Diamond | 56.1% | 189 | Epoch AI run, accuracy | Independent run | Apr 1, 2025 |
| MMLU-Pro | 76.1% | 82 | Overall accuracy; data source: Self-Reported | Vendor-reported | Mar 11, 2026 |
| AIME (OTIS Mock AIME 2024–2025) | 16.1% | 211 | Epoch AI run, OTIS Mock AIME 2024–2025 | Independent run | Apr 1, 2025 |
| MATH Level 5 | 67.2% | 45 | Epoch AI run, accuracy | Independent run | Apr 1, 2025 |
FAQ
Where do these Qwen2.5-Max scores come from?
From Epoch AI Benchmarking Hub, LMArena leaderboard dataset, and MMLU-Pro leaderboard (TIGER-Lab). Each row links to the original leaderboard, dataset or report, and vendor-reported numbers are labelled.