llm-benchmarks
githubdrose.io

GPT-6.2 Sol Pro Benchmarks


Measured on azure

3 runs
azure site
Avg Tokens / Second
63.10
Decode Tokens / Second
—
Avg Time to First Token (ms)
8110.00
Runs Analysed
3
Last Updated
Nov 18, 2026, 07:35 PM

Throughput distribution

Throughput over time

GPT-6.2 Sol Proazure64tok/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 72 tok/s (99th percentile) · dashed rule is the model's own mean · 1 cell carry fewer than 4 samples

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 OpenRouter63.1049.5071.408110.003

Frequently Asked Questions

How fast is GPT-6.2 Sol Pro?
The latest rolling average throughput is 63.10 tokens per second with an average time to first token of 8110.00 ms across 3 recent runs.
How often are these benchmarks updated?
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Nov 18, 2026, 07:35 PM.

Related models