llm-benchmarks
githubdrose.io

gemini-2.5-pro Benchmarks


Measured on google

6 runs
google site
Avg Tokens / Second
1.52
Avg Time to First Token (ms)
1540.00
Runs Analysed
6
Last Updated
Aug 4, 2026, 01:18 PM

Throughput distribution

  • gemini-2.5-pro google2 tok/s
025

Visible-token throughput, same basis as the table · curves normalised per model

Throughput over time

gemini-2.5-progoogle0tok/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 1 tok/s (99th percentile) · dashed rule is the model's own mean · 1 samples above the ceiling drawn at it

Every provider serving this model

1 measured
ProviderModelAvg Toks/SecMinMaxAvg TTF (ms)
googlegemini-2.5-pro1.520.612.161540.00

Frequently Asked Questions

How fast is gemini-2.5-pro?
The latest rolling average throughput is 1.52 tokens per second with an average time to first token of 1540.00 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 Aug 4, 2026, 01:18 PM.

Related models