llm-benchmarks
githubdrose.io

GPT-6 Luna Pro Benchmarks


Measured on azure

6 runs
azure site
Avg Tokens / Second
89.60
Decode Tokens / Second
—
Avg Time to First Token (ms)
20100.00
Runs Analysed
6
Last Updated
Sep 24, 2026, 07:18 PM

Throughput distribution

Throughput over time

GPT-6 Luna Proazure95tok/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 · models with at least 4 samples in the window first, fastest of those at the top · shared vertical scale, 0 to 119 tok/s (99th percentile) · dashed rule is the model's own mean

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
azurevia OpenRouter89.6076.00107.0020100.006

Frequently Asked Questions

How fast is GPT-6 Luna Pro?
The latest rolling average throughput is 89.60 tokens per second with an average time to first token of 20100.00 ms across 6 recent runs.
How often are these benchmarks updated?
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Sep 24, 2026, 07:18 PM.

Related models