Model record
Qwen2.5-Max model overview
Qwen2.5-Max is a api model from Alibaba. It was released on January 29, 2025. Its strongest case is strong multilingual coverage, while buyers should account for core weights are not available.
Qwen2.5-Max benchmark snapshot
| Evaluation | Reported score | What it probes |
|---|---|---|
| MMLU-Pro | 76.1 | Broad knowledge and multi-step reasoning |
| GPQA Diamond | 60.1 | Graduate-level science reasoning |
| SWE-bench Verified | 38.8 | Verified real-repository issue resolution |
| LiveCodeBench | 38.7 | Contamination-aware competitive programming |
| SWE-Bench Pro | Not reported | Longer, harder professional software tasks |
| Artificial Analysis Intelligence Index | Not reported | Composite third-party capability index; version matters |
Scores are percentages reported by model creators or benchmark maintainers under varying settings. A blank is preferable to an inferred result. See our methodology.
Qwen2.5-Max strengths
- Strong multilingual coverage
- Competitive general reasoning
- MoE architecture
Qwen2.5-Max limitations
- Core weights are not available
- Shorter context than some peers
Editorial take: Benchmark rank should narrow a shortlist, not close a purchase. Run a private evaluation with representative prompts, failure cases, latency targets, and total token costs.
Compare Qwen2.5-Max
- Qwen2.5-Max vs DeepSeek R1 — review fit, trade-offs, listed prices, and an evaluation plan.
Source record
Specifications and scores are linked to the best source located during review. Provider-reported results are not presented as third-party lab reproductions.
Read Qwen model announcement ↗