gemini-2.5-pro Benchmarks

Provider: google

Explore real-world latency and throughput results for gemini-2.5-pro. These measurements come from automated benchmarking runs against the provider APIs using the same harness that powers the public cloud dashboard.

Want a broader view of this vendor? Visit the google provider hub to compare every tracked model side-by-side.

Visit google Official Website

Benchmark Overview

Avg Tokens / Second

55.10

Avg Time to First Token (ms)

0.75

Runs Analysed

1

Last Updated

Dec 8, 2025, 11:59 PM

Key Insights

  • gemini-2.5-pro streams at 55.10 tokens/second on average across the last 1 benchmark runs.

  • Performance fluctuated by 0.00 tokens/second (0.0% coefficient of variation), indicating consistent behavior across benchmark runs.

  • Average time to first token is 0.75 ms (excellent latency), suitable for latency-sensitive workloads.

  • Latest measurements completed on Dec 8, 2025, 11:59 PM based on 1 total samples.

Performance Distribution

Distribution of throughput measurements showing performance consistency across benchmark runs.

Performance Over Time

Historical performance trends showing how throughput has changed over the benchmarking period.

gemini-2.5-pro

Benchmark Samples

ProviderModelAvg Toks/SecMinMaxAvg TTF (ms)
googlegemini-2.5-pro55.1055.1055.100.75

Frequently Asked Questions

The latest rolling average throughput is 55.10 tokens per second with an average time to first token of 0.75 ms across 1 recent runs.

Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Dec 8, 2025, 11:59 PM.

Related Links