GLM 4.7 vs NVIDIA Nemotron 3 Super 120B A12B
Zhipu AI vs NVIDIA — benchmarks, pricing, and capabilities side by side.
- •GLM 4.7 has the higher intelligence index (89 vs 80)
- •NVIDIA Nemotron 3 Super 120B A12B is cheaper ($0.30 vs $0.40 per 1M input)
- •NVIDIA Nemotron 3 Super 120B A12B is faster
| GLM 4.7 | NVIDIA Nemotron 3 Super 120B A12B | |
|---|---|---|
| Intelligence index | 89 | 80 |
| Developer | Zhipu AI | NVIDIA |
| Type | LLM | LLM |
| Access | Open weights | — |
| Context window | 202,752 tokens | — |
| Input price | $0.40 / 1M | $0.30 / 1M |
| Output price | $1.75 / 1M | $0.80 / 1M |
| Speed | 98 tok/s | 211 tok/s |
| Released | December 22, 2025 | March 11, 2026 |
| Parameters | — | — |
| Input modalities | Text | — |
| Output modalities | Text | — |
Shared benchmarks
GLM 4.7
NVIDIA Nemotron 3 Super 120B A12B
GPQA Diamond
85.9
80
Humanity’s Last Exam
25.1
19.2