DeepSeek-V4-Flash vs GLM 5 Turbo
DeepSeek vs Zhipu AI — benchmarks, pricing, and capabilities side by side.
- •DeepSeek-V4-Flash has the higher intelligence index (89.4 vs 84.7)
- •DeepSeek-V4-Flash is cheaper ($0.10 vs $1.20 per 1M input)
- •DeepSeek-V4-Flash has a larger context window (1M)
| DeepSeek-V4-Flash | GLM 5 Turbo | |
|---|---|---|
| Intelligence index | 89.4 | 84.7 |
| Developer | DeepSeek | Zhipu AI |
| Type | LLM | LLM |
| Access | Open weights | API only |
| Context window | 1,048,576 tokens | 202,752 tokens |
| Input price | $0.10 / 1M | $1.20 / 1M |
| Output price | $0.20 / 1M | $4.00 / 1M |
| Speed | 109 tok/s | — |
| Released | April 24, 2026 | March 15, 2026 |
| Parameters | 284B (13B active) | — |
| Input modalities | Text | Text |
| Output modalities | Text | Text |
Shared benchmarks
DeepSeek-V4-Flash
GLM 5 Turbo
GPQA Diamond
89.4
84.7
Humanity’s Last Exam
32.1
25.4