GLM 4.7 vs Hermes 4 - Llama-3.1 405B
Zhipu AI vs Nous Research — benchmarks, pricing, and capabilities side by side.
- •GLM 4.7 has the higher intelligence index (89 vs 73.5)
- •GLM 4.7 is cheaper ($0.40 vs $1.00 per 1M input)
- •GLM 4.7 is faster
| GLM 4.7 | Hermes 4 - Llama-3.1 405B | |
|---|---|---|
| Intelligence index | 89 | 73.5 |
| Developer | Zhipu AI | Nous Research |
| Type | LLM | LLM |
| Access | Open weights | — |
| Context window | 202,752 tokens | — |
| Input price | $0.40 / 1M | $1.00 / 1M |
| Output price | $1.75 / 1M | $3.00 / 1M |
| Speed | 98 tok/s | 34 tok/s |
| Released | December 22, 2025 | August 27, 2025 |
| Parameters | — | — |
| Input modalities | Text | — |
| Output modalities | Text | — |
Shared benchmarks
GLM 4.7
Hermes 4 - Llama-3.1 405B
AIME 2025
95
69.7
GPQA Diamond
85.9
72.7
Humanity’s Last Exam
25.1
10.3
LiveCodeBench
89.4
68.6
MMLU-Pro
85.6
82.9