GLM 4.7 vs Llama 3.1 70B Instruct
Zhipu AI vs Meta — benchmarks, pricing, and capabilities side by side.
- •GLM 4.7 has the higher intelligence index (89 vs 56)
- •Llama 3.1 70B Instruct is faster
- •GLM 4.7 has a larger context window (203K)
| GLM 4.7 | Llama 3.1 70B Instruct | |
|---|---|---|
| Intelligence index | 89 | 56 |
| Developer | Zhipu AI | Meta |
| Type | LLM | LLM |
| Access | Open weights | Open weights |
| Context window | 202,752 tokens | 131,072 tokens |
| Input price | $0.40 / 1M | $0.40 / 1M |
| Output price | $1.75 / 1M | $0.40 / 1M |
| Speed | 98 tok/s | 1204 tok/s |
| Released | December 22, 2025 | July 23, 2024 |
| Parameters | — | — |
| Input modalities | Text | Text |
| Output modalities | Text | Text |
Shared benchmarks
GLM 4.7
Llama 3.1 70B Instruct
AIME 2025
95
4
GPQA Diamond
85.9
41.7
Humanity’s Last Exam
25.1
4.6
LiveCodeBench
89.4
23.2
MMLU-Pro
85.6
66.4