Qwen2.5 VL 72B Instruct vs Qwen3.5 397B A17B
Alibaba vs Alibaba — benchmarks, pricing, and capabilities side by side.
- •Qwen3.5 397B A17B has the higher intelligence index (89.3 vs 79.1)
- •Qwen2.5 VL 72B Instruct is cheaper ($0.25 vs $0.39 per 1M input)
- •Qwen3.5 397B A17B has a larger context window (262K)
| Qwen2.5 VL 72B Instruct | Qwen3.5 397B A17B | |
|---|---|---|
| Intelligence index | 79.1 | 89.3 |
| Developer | Alibaba | Alibaba |
| Type | Multimodal | Multimodal |
| Access | Open weights | Open weights |
| Context window | 131,072 tokens | 262,144 tokens |
| Input price | $0.25 / 1M | $0.39 / 1M |
| Output price | $0.75 / 1M | $2.34 / 1M |
| Speed | — | 53 tok/s |
| Released | February 1, 2025 | February 16, 2026 |
| Parameters | — | — |
| Input modalities | Text, Image | Text, Image, Video |
| Output modalities | Text | Text |