Mistral Small 4 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 76.9)
- •Mistral Small 4 is cheaper ($0.15 vs $0.39 per 1M input)
- •Mistral Small 4 is faster
| Mistral Small 4 | Qwen3.5 397B A17B | |
|---|---|---|
| Intelligence index | 76.9 | 89.3 |
| Developer | Mistral AI | Alibaba |
| Type | Multimodal | Multimodal |
| Access | Open weights | Open weights |
| Context window | 262,144 tokens | 262,144 tokens |
| Input price | $0.15 / 1M | $0.39 / 1M |
| Output price | $0.60 / 1M | $2.34 / 1M |
| Speed | 145 tok/s | 53 tok/s |
| Released | March 16, 2026 | February 16, 2026 |
| Parameters | — | — |
| Input modalities | Text, Image | Text, Image, Video |
| Output modalities | Text | Text |
Shared benchmarks
Mistral Small 4
Qwen3.5 397B A17B
GPQA Diamond
76.9
89.3
Humanity’s Last Exam
9.5
27.3