llm-benchmarks
githubdrose.io

Google: Nano Banana (Gemini 2.5 Flash Image) Benchmarks


Measured on google

661 runs
google site
Avg Tokens / Second
160.00
Avg Time to First Token (ms)
930.00
Runs Analysed
661
Last Updated
Aug 13, 2026, 02:57 PM

Throughput distribution

Throughput over time

Google: Nano Banana (Gemini 2.5 Flash Image)google118tok/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 235 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)
googleGoogle: Nano Banana (Gemini 2.5 Flash Image)160.0018.30251.00930.00

Frequently Asked Questions

How fast is Google: Nano Banana (Gemini 2.5 Flash Image)?
The latest rolling average throughput is 160.00 tokens per second with an average time to first token of 930.00 ms across 661 recent runs.
How often are these benchmarks updated?
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Aug 13, 2026, 02:57 PM.

Related models