Claude 3.5 Haiku vs GLM 4.7
Anthropic vs Zhipu AI — benchmarks, pricing, and capabilities side by side.
- •GLM 4.7 has the higher intelligence index (89 vs 54.5)
- •GLM 4.7 is cheaper ($0.40 vs $0.80 per 1M input)
- •Claude 3.5 Haiku is faster
- •GLM 4.7 has a larger context window (203K)
| Claude 3.5 Haiku | GLM 4.7 | |
|---|---|---|
| Intelligence index | 54.5 | 89 |
| Developer | Anthropic | Zhipu AI |
| Type | LLM | LLM |
| Access | API only | Open weights |
| Context window | 200,000 tokens | 202,752 tokens |
| Input price | $0.80 / 1M | $0.40 / 1M |
| Output price | $4.00 / 1M | $1.75 / 1M |
| Speed | 104 tok/s | 98 tok/s |
| Released | November 4, 2024 | December 22, 2025 |
| Parameters | — | — |
| Input modalities | Text, Image | Text |
| Output modalities | Text | Text |
Shared benchmarks
Claude 3.5 Haiku
GLM 4.7
GPQA Diamond
41.6
85.9
Humanity’s Last Exam
3.5
25.1
LiveCodeBench
31.4
89.4
MMLU-Pro
65
85.6