Devstral Small vs GLM 4.7
Mistral AI vs Zhipu AI — benchmarks, pricing, and capabilities side by side.
- •GLM 4.7 has the higher intelligence index (89 vs 45.3)
- •Devstral Small is cheaper ($0.10 vs $0.40 per 1M input)
- •Devstral Small is faster
| Devstral Small | GLM 4.7 | |
|---|---|---|
| Intelligence index | 45.3 | 89 |
| Developer | Mistral AI | Zhipu AI |
| Type | LLM | LLM |
| Access | — | Open weights |
| Context window | — | 202,752 tokens |
| Input price | $0.10 / 1M | $0.40 / 1M |
| Output price | $0.30 / 1M | $1.75 / 1M |
| Speed | 190 tok/s | 98 tok/s |
| Released | May 21, 2025 | December 22, 2025 |
| Parameters | — | — |
| Input modalities | — | Text |
| Output modalities | — | Text |
Shared benchmarks
Devstral Small
GLM 4.7
AIME 2025
29.3
95
GPQA Diamond
43.4
85.9
Humanity’s Last Exam
4
25.1
LiveCodeBench
25.8
89.4
MMLU-Pro
63.2
85.6