GLM 4.7 vs Kimi K2 Thinking
Zhipu AI vs Moonshot AI — benchmarks, pricing, and capabilities side by side.
- •GLM 4.7 has the higher intelligence index (89 vs 85.6)
- •GLM 4.7 is cheaper ($0.40 vs $0.60 per 1M input)
- •Kimi K2 Thinking is faster
- •Kimi K2 Thinking has a larger context window (262K)
| GLM 4.7 | Kimi K2 Thinking | |
|---|---|---|
| Intelligence index | 89 | 85.6 |
| Developer | Zhipu AI | Moonshot AI |
| Type | LLM | LLM |
| Access | Open weights | Open weights |
| Context window | 202,752 tokens | 262,144 tokens |
| Input price | $0.40 / 1M | $0.60 / 1M |
| Output price | $1.75 / 1M | $2.50 / 1M |
| Speed | 98 tok/s | 100 tok/s |
| Released | December 22, 2025 | November 6, 2025 |
| Parameters | — | 1T (32B active) |
| Input modalities | Text | Text |
| Output modalities | Text | Text |
Shared benchmarks
GLM 4.7
Kimi K2 Thinking
AIME 2025
95
94.7
GPQA Diamond
85.9
84.5
Humanity’s Last Exam
25.1
22.3
LiveCodeBench
89.4
85.3
MMLU-Pro
85.6
84.8