llm-benchmarks
githubdrose.io

GLM 5 Benchmarks


Measured on gmicloud

1 runs
Avg Tokens / Second
2.71
Decode Tokens / Second
—
Avg Time to First Token (ms)
22600.00
Runs Analysed
1
Last Updated
Oct 5, 2026, 09:01 AM

Throughput distribution

Throughput over time

No time series data available.

Every lane measuring this model

1 measured · live first · a lane is a provider, a catalogue id and a transport
ProviderLaneAvg Toks/SecMinMaxAvg TTF (ms)n
gmicloudvia OpenRouter2.712.712.7122600.001

Frequently Asked Questions

How fast is GLM 5?
The latest rolling average throughput is 2.71 tokens per second with an average time to first token of 22600.00 ms across 1 recent runs.
How often are these benchmarks updated?
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Oct 5, 2026, 09:01 AM.

Related models