DeepSeek-V3.1 vs GLM 4.7
DeepSeek vs Zhipu AI — benchmarks, pricing, and capabilities side by side.
- •GLM 4.7 has the higher intelligence index (89 vs 59.8)
- •DeepSeek-V3.1 is cheaper ($0.21 vs $0.40 per 1M input)
- •GLM 4.7 has a larger context window (203K)
| DeepSeek-V3.1 | GLM 4.7 | |
|---|---|---|
| Intelligence index | 59.8 | 89 |
| Developer | DeepSeek | Zhipu AI |
| Type | LLM | LLM |
| Access | Open weights | Open weights |
| Context window | 163,840 tokens | 202,752 tokens |
| Input price | $0.21 / 1M | $0.40 / 1M |
| Output price | $0.79 / 1M | $1.75 / 1M |
| Speed | — | 98 tok/s |
| Released | August 21, 2025 | December 22, 2025 |
| Parameters | 671B (37B active) | — |
| Input modalities | Text | Text |
| Output modalities | Text | Text |
Shared benchmarks
DeepSeek-V3.1
GLM 4.7
AIME 2025
49.8
95
GPQA Diamond
74.9
85.9
Humanity’s Last Exam
15.9
25.1
LiveCodeBench
56.4
89.4
MMLU-Pro
83.7
85.6