GLM 4.7 vs Qwen3 30B A3B 2507 Instruct
Zhipu AI vs Alibaba — benchmarks, pricing, and capabilities side by side.
- •GLM 4.7 has the higher intelligence index (89 vs 69.3)
- •Qwen3 30B A3B 2507 Instruct is cheaper ($0.20 vs $0.40 per 1M input)
- •Qwen3 30B A3B 2507 Instruct is faster
| GLM 4.7 | Qwen3 30B A3B 2507 Instruct | |
|---|---|---|
| Intelligence index | 89 | 69.3 |
| Developer | Zhipu AI | Alibaba |
| Type | LLM | LLM |
| Access | Open weights | — |
| Context window | 202,752 tokens | — |
| Input price | $0.40 / 1M | $0.20 / 1M |
| Output price | $1.75 / 1M | $0.40 / 1M |
| Speed | 98 tok/s | 122 tok/s |
| Released | December 22, 2025 | July 29, 2025 |
| Parameters | — | — |
| Input modalities | Text | — |
| Output modalities | Text | — |
Shared benchmarks
GLM 4.7
Qwen3 30B A3B 2507 Instruct
AIME 2025
95
66.3
GPQA Diamond
85.9
65.9
Humanity’s Last Exam
25.1
6.8
LiveCodeBench
89.4
51.5
MMLU-Pro
85.6
77.7