GLM 4.7 vs Phi-3 Mini Instruct 3.8B
Zhipu AI vs Microsoft — benchmarks, pricing, and capabilities side by side.
- •GLM 4.7 has the higher intelligence index (89 vs 27.5)
- •Phi-3 Mini Instruct 3.8B is cheaper ($0.00 vs $0.40 per 1M input)
| GLM 4.7 | Phi-3 Mini Instruct 3.8B | |
|---|---|---|
| Intelligence index | 89 | 27.5 |
| Developer | Zhipu AI | Microsoft |
| Type | LLM | LLM |
| Access | Open weights | — |
| Context window | 202,752 tokens | — |
| Input price | $0.40 / 1M | $0.00 / 1M |
| Output price | $1.75 / 1M | $0.00 / 1M |
| Speed | 98 tok/s | — |
| Released | December 22, 2025 | April 23, 2024 |
| Parameters | — | — |
| Input modalities | Text | — |
| Output modalities | Text | — |
Shared benchmarks
GLM 4.7
Phi-3 Mini Instruct 3.8B
AIME 2025
95
0.3
GPQA Diamond
85.9
31.9
Humanity’s Last Exam
25.1
4.4
LiveCodeBench
89.4
11.6
MMLU-Pro
85.6
43.5