GLM 4.7 vs Granite 3.3 8B
Zhipu AI vs IBM — benchmarks, pricing, and capabilities side by side.
- •GLM 4.7 has the higher intelligence index (89 vs 32.5)
- •Granite 3.3 8B is cheaper ($0.00 vs $0.40 per 1M input)
- •Granite 3.3 8B is faster
| GLM 4.7 | Granite 3.3 8B | |
|---|---|---|
| Intelligence index | 89 | 32.5 |
| Developer | Zhipu AI | IBM |
| Type | LLM | LLM |
| Access | Open weights | — |
| Context window | 202,752 tokens | — |
| Input price | $0.40 / 1M | $0.00 / 1M |
| Output price | $1.75 / 1M | $0.30 / 1M |
| Speed | 98 tok/s | 376 tok/s |
| Released | December 22, 2025 | April 16, 2025 |
| Parameters | — | — |
| Input modalities | Text | — |
| Output modalities | Text | — |
Shared benchmarks
GLM 4.7
Granite 3.3 8B
AIME 2025
95
6.7
GPQA Diamond
85.9
33.8
Humanity’s Last Exam
25.1
4.2
LiveCodeBench
89.4
12.7
MMLU-Pro
85.6
46.8