10models tracked · ranked by intelligence, speed & price
Z.ai's smartest model is GLM 5 Turbo (46.8 on the Intelligence Index), its fastest is GLM 4.7 at 412 tokens/sec, and its cheapest is GLM 4.7 Flash at $0.060 per million input tokens. All 10 Z.ai models are compared below by intelligence, speed, latency, context and price.
| Model | Intel | Speed | Latency | In $/M | Context |
|---|---|---|---|---|---|
| glm-5-turbo ReasoningToolsJSON | 46.8 | 21 | 1.6s | $1.20 | 262K |
| glm-5.1 ReasoningToolsJSON | 43.8 | 71 | 281ms | $0.980 | 203K |
| glm-4.7 ReasoningToolsJSON | 42.1 | 412 | 636ms | $0.400 | 203K |
| glm-5 ReasoningToolsJSON | 40.6 | 92 | 304ms | $0.600 | 203K |
| glm-4.6 ReasoningToolsJSON | 30.2 | 38 | 674ms | $0.430 | 203K |
| glm-4.7-flash ReasoningToolsJSON | 30.1 | 37 | 333ms | $0.060 | 203K |
| glm-4.5 ReasoningToolsJSON | 26.4 | 26 | 1.6s | $0.600 | 131K |
| glm-4.6v ReasoningToolsJSON+1 | 23.4 | 65 | 1.3s | $0.300 | 131K |
| glm-4.5-air ReasoningToolsJSON | 23.2 | 48 | 760ms | $0.125 | 131K |
| glm-4.5v ReasoningToolsJSON+1 | 15.1 | 43 | 1.1s | $0.600 | 66K |