Manufacturer

Z.ai (Zhipu)

GLM-Modellfamilie von Z.ai / Zhipu AI.

3Models

79Benchmarks

79Performance

0Harness

Best token generation

661,8 tok/s

GLM-4.5-Air

Best prefill

14.193,4 tok/s

glm-4.7-flash

∅ Token generation

107,6 tok/s

Average of 79 runs

∅ Prefill

2.359,9 tok/s

Average of 79 runs

Best TTFT

346 ms

glm-4.7-flash

Best harness rate

no harness run yet

🏆

GLM-4.5-Air · fastest model at 661,8 tok/s token generation
Best prefill of this manufacturer: 14.193,4 tok/s (glm-4.7-flash)

Best measured generation throughput per model (tok/s), published performance benchmarks.

GLM-4.5-Air

661,8 tok/s

glm-4.7-flash

349,3 tok/s

glm-5.2-colibri

0,0 tok/s

Models

3 assigned