llm-benchmarks
githubdrose.io

GPT-6.2 Astra Pro Benchmarks


Measured on azure

18 runs
azure site
Avg Tokens / Second
15.70
Decode Tokens / Second
—
Avg Time to First Token (ms)
8390.00
Runs Analysed
18
Last Updated
Nov 22, 2026, 06:13 AM

Throughput distribution

Throughput over time

GPT-6.2 Astra Proazure16tok/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 24 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 OpenRouter15.706.1122.508390.0018

Frequently Asked Questions

How fast is GPT-6.2 Astra Pro?
The latest rolling average throughput is 15.70 tokens per second with an average time to first token of 8390.00 ms across 18 recent runs.
How often are these benchmarks updated?
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Nov 22, 2026, 06:13 AM.

Related models