GLM 4.7 vs Llama Nemotron Super 49B v1.5
Zhipu AI vs NVIDIA — benchmarks, pricing, and capabilities side by side.
- •GLM 4.7 has the higher intelligence index (89 vs 79.4)
- •Llama Nemotron Super 49B v1.5 is cheaper ($0.10 vs $0.40 per 1M input)
- •GLM 4.7 is faster
| GLM 4.7 | Llama Nemotron Super 49B v1.5 | |
|---|---|---|
| Intelligence index | 89 | 79.4 |
| Developer | Zhipu AI | NVIDIA |
| Type | LLM | LLM |
| Access | Open weights | — |
| Context window | 202,752 tokens | — |
| Input price | $0.40 / 1M | $0.10 / 1M |
| Output price | $1.75 / 1M | $0.40 / 1M |
| Speed | 98 tok/s | 51 tok/s |
| Released | December 22, 2025 | July 25, 2025 |
| Parameters | — | — |
| Input modalities | Text | — |
| Output modalities | Text | — |
Shared benchmarks
GLM 4.7
Llama Nemotron Super 49B v1.5
AIME 2025
95
76.7
GPQA Diamond
85.9
74.8
Humanity’s Last Exam
25.1
6.8
LiveCodeBench
89.4
73.7
MMLU-Pro
85.6
81.4