Qwen2.5 72B Instruct vs Qwen3.6 Max
Alibaba vs Alibaba — benchmarks, pricing, and capabilities side by side.
- •Qwen3.6 Max has the higher intelligence index (88.8 vs 59.1)
- •Qwen2.5 72B Instruct is cheaper ($0.36 vs $1.04 per 1M input)
- •Qwen2.5 72B Instruct is faster
- •Qwen3.6 Max has a larger context window (262K)
| Qwen2.5 72B Instruct | Qwen3.6 Max | |
|---|---|---|
| Intelligence index | 59.1 | 88.8 |
| Developer | Alibaba | Alibaba |
| Type | LLM | LLM |
| Access | Open weights | API only |
| Context window | 131,072 tokens | 262,144 tokens |
| Input price | $0.36 / 1M | $1.04 / 1M |
| Output price | $0.40 / 1M | $6.24 / 1M |
| Speed | 100 tok/s | 36 tok/s |
| Released | September 19, 2024 | April 27, 2026 |
| Parameters | — | — |
| Input modalities | Text | Text |
| Output modalities | Text | Text |
Shared benchmarks
Qwen2.5 72B Instruct
Qwen3.6 Max
GPQA Diamond
49
88.8
Humanity’s Last Exam
4.2
28.9