llm-benchmarks
githubdrose.io

GLM 4.5 Air Benchmarks


Measured on siliconflow

8 runs
Avg Tokens / Second
15.90
Avg Time to First Token (ms)
4930.00
Runs Analysed
8
Last Updated
Aug 18, 2026, 06:32 PM

Throughput distribution

Throughput over time

GLM 4.5 Airz-ai1tok/s

Generated throughput, including reasoning tokens — so a thinking model's line does not collapse; the table ranks on visible tokens · one cell per model, showing its best-covered provider · shared vertical scale, 0 to 60 tok/s (99th percentile) · dashed rule is the model's own mean · 3 further providers not drawn · 1 samples above the ceiling drawn at it

Every provider serving this model

1 measured
ProviderModelAvg Toks/SecMinMaxAvg TTF (ms)
siliconflowGLM 4.5 Air15.908.1531.004930.00

Frequently Asked Questions

How fast is GLM 4.5 Air?
The latest rolling average throughput is 15.90 tokens per second with an average time to first token of 4930.00 ms across 8 recent runs.
How often are these benchmarks updated?
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Aug 18, 2026, 06:32 PM.

Related models