Side-by-side comparison of Qwen 2.5 (Alibaba) and Qwen 3.5 397B-A17B (Alibaba) — benchmarks, pricing, and capabilities.
| Qwen 2.5 Alibaba | Qwen 3.5 397B-A17B Alibaba | |
|---|---|---|
| Category | LLMs | LLMs |
| Specifications | ||
| Context Window | 128K | 256K |
| Pricing (per 1M tokens) | ||
| Input Cost | Free | Free |
| Output Cost | Free | Free |
| Performance | ||
| Overall Score | 83.8 | 89.2 |
| ARC-Challenge | — | 91.4 |
| BigBench Hard | 75.8 | 84.0 |
| Chatbot Arena ELO | — | 1150.0 |
| DROP | 76.0 | 84.5 |
| GSM8K | 85.0 | 91.5 |
| HumanEval | 76.2 | 87.0 |
| MATH | 61.2 | 71.0 |
| MMLU | 81.5 | 86.5 |
| TruthfulQA | 57.0 | 55.8 |
| WinoGrande | — | 78.4 |
| Community | ||
| User Rating | ★ 4.3 | ★ 4.5 |
| Reviews | 198 | 156 |