llm-benchmarks
githubdrose.io

Nano Banana 2 (Gemini 3.1 Flash Image Preview) Benchmarks


Measured on google

2 runs
google site
Avg Tokens / Second
69.80
Decode Tokens / Second
—
Avg Time to First Token (ms)
990.00
Runs Analysed
2
Last Updated
Oct 23, 2026, 07:43 AM

Throughput distribution

Throughput over time

Nano Banana 2 (Gemini 3.1 Flash Image Preview)google70tok/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 81 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
googlevia OpenRouter69.8062.0077.60990.002

Frequently Asked Questions

How fast is Nano Banana 2 (Gemini 3.1 Flash Image Preview)?
The latest rolling average throughput is 69.80 tokens per second with an average time to first token of 990.00 ms across 2 recent runs.
How often are these benchmarks updated?
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Oct 23, 2026, 07:43 AM.

Related models