DeepHermes 3 - Mistral 24B vs GLM 4.7
Nous Research vs Zhipu AI — benchmarks, pricing, and capabilities side by side.
- •GLM 4.7 has the higher intelligence index (89 vs 43.8)
- •DeepHermes 3 - Mistral 24B is cheaper ($0.00 vs $0.40 per 1M input)
| DeepHermes 3 - Mistral 24B | GLM 4.7 | |
|---|---|---|
| Intelligence index | 43.8 | 89 |
| Developer | Nous Research | Zhipu AI |
| Type | LLM | LLM |
| Access | — | Open weights |
| Context window | — | 202,752 tokens |
| Input price | $0.00 / 1M | $0.40 / 1M |
| Output price | $0.00 / 1M | $1.75 / 1M |
| Speed | — | 98 tok/s |
| Released | March 13, 2025 | December 22, 2025 |
| Parameters | — | — |
| Input modalities | — | Text |
| Output modalities | — | Text |
Shared benchmarks
DeepHermes 3 - Mistral 24B
GLM 4.7
GPQA Diamond
38.2
85.9
Humanity’s Last Exam
3.9
25.1
LiveCodeBench
19.5
89.4
MMLU-Pro
58
85.6