Mistral Medium 3 vs Qwen3.5 397B A17B
Mistral AI vs Alibaba — benchmarks, pricing, and capabilities side by side.
- •Qwen3.5 397B A17B has the higher intelligence index (89.3 vs 58.6)
- •Qwen3.5 397B A17B is cheaper ($0.39 vs $0.40 per 1M input)
- •Qwen3.5 397B A17B is faster
- •Qwen3.5 397B A17B has a larger context window (262K)
| Mistral Medium 3 | Qwen3.5 397B A17B | |
|---|---|---|
| Intelligence index | 58.6 | 89.3 |
| Developer | Mistral AI | Alibaba |
| Type | Multimodal | Multimodal |
| Access | API only | Open weights |
| Context window | 131,072 tokens | 262,144 tokens |
| Input price | $0.40 / 1M | $0.39 / 1M |
| Output price | $2.00 / 1M | $2.34 / 1M |
| Speed | 32 tok/s | 53 tok/s |
| Released | May 7, 2025 | February 16, 2026 |
| Parameters | — | — |
| Input modalities | Text, Image | Text, Image, Video |
| Output modalities | Text | Text |
Shared benchmarks
Mistral Medium 3
Qwen3.5 397B A17B
GPQA Diamond
57.8
89.3
Humanity’s Last Exam
4.3
27.3