Alibaba (Qwen)
Qwen2.5-7B benchmark results
5 results on 5 benchmarks from 3 sources.
Open weights Released: Sep 19, 2024 Updated Oct 22, 2026
Also listed as: qwen2.5-7b-instruct · Qwen2.5 Instruct Turbo (7B) · Qwen/Qwen2.5-7B-Instruct · Qwen/Qwen2.5-7B
All benchmark results
| Benchmarks | Score | Rank | Setting | Source type | Date |
|---|---|---|---|---|---|
| Open LLM Leaderboard v2 | 35.2% | 623 | Average of 6 normalised benchmarks; bfloat16; 7.616B params“Qwen/Qwen2.5-7B-Instruct” | Official leaderboard | Mar 13, 2025 |
| GPQA Diamond | 35.5% | 248 | Epoch AI run, accuracy | Independent run | Aug 30, 2026 |
| MMLU | 72.9% | 47 | Exact match; 5-shot | Official leaderboard via Epoch AI | Sep 19, 2024 |
| MMLU-Pro | 45.0% | 176 | Overall accuracy; data source: Self-Reported; 7B | Vendor-reported | Mar 11, 2026 |
| AIME (OTIS Mock AIME 2024–2025) | 2.5% | 244 | Epoch AI run, OTIS Mock AIME 2024–2025 | Independent run | Aug 30, 2026 |
FAQ
Where do these Qwen2.5-7B 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.