Granite 4.0 H Small vs Qwen3.7 Max
IBM vs Alibaba — benchmarks, pricing, and capabilities side by side.
- •Qwen3.7 Max has the higher intelligence index (92.3 vs 35.7)
- •Granite 4.0 H Small is cheaper ($0.10 vs $2.50 per 1M input)
- •Granite 4.0 H Small is faster
| Granite 4.0 H Small | Qwen3.7 Max | |
|---|---|---|
| Intelligence index | 35.7 | 92.3 |
| Developer | IBM | Alibaba |
| Type | LLM | LLM |
| Access | — | API only |
| Context window | — | 1,000,000 tokens |
| Input price | $0.10 / 1M | $2.50 / 1M |
| Output price | $0.30 / 1M | $7.50 / 1M |
| Speed | 524 tok/s | 203 tok/s |
| Released | September 22, 2025 | May 21, 2026 |
| Parameters | — | — |
| Input modalities | — | Text |
| Output modalities | — | Text |
Shared benchmarks
Granite 4.0 H Small
Qwen3.7 Max
GPQA Diamond
41.6
92.3
Humanity’s Last Exam
3.7
38.1