Qwen2.5-Max
- Made by
- Alibaba
- Released
- Announced in
- Qwen2.5-Max: Exploring the Intelligence of Large-scale MoE Modelqwen.ai
- Event
- Qwen2.5-Max
- API record
- /api/v1/models/qwen2-5-max
Benchmark results
| Benchmark | Score | Source check |
|---|---|---|
| GPQA Diamondinstruct model | 60.1% | CheckedA person checked this number against its source on 19 Oct 2026. This confirms the number matches what the lab published, not that the score was reproduced. |
| MMLU-Proinstruct model | 76.1% | CheckedA person checked this number against its source on 19 Oct 2026. This confirms the number matches what the lab published, not that the score was reproduced. |
| LiveCodeBenchinstruct model; problems from Aug to Nov 2024 | 38.7% | CheckedA person checked this number against its source on 19 Oct 2026. This confirms the number matches what the lab published, not that the score was reproduced. |
Sources
Reported by Alibaba
- Qwen2.5-Max: Exploring the Intelligence of Large-scale MoE Modelqwen.ai · 28 Jan 2025
Original image
