llm-benchmarks
githubdrose.io

google Provider Benchmarks


Measured over the last 30 days

Models Tracked
21
Avg Tokens / Second
34.51
Avg Time to First Token (ms)
4182.38
Last Updated
Oct 28, 2026

All google models

21 live · one row per model · fastest first · 1 retired lanes not listed · 2 folded behind their current lane
google site
ModelAvg Toks/SecMinMaxAvg TTF (ms)
Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)82.1075.4088.80780.00
Gemini 2.5 Flash Lite76.5073.7079.30610.00
Nano Banana 2 (Gemini 3.1 Flash Image Preview)69.8062.0077.60990.00
Gemini 3.5 Flash Lite68.6066.8070.30690.00
Gemini 3.1 Flash Lite Preview68.1063.3072.80790.00
Nano Banana 2 (Gemini 3.1 Flash Image)65.0061.1068.901160.00
Gemini 3.1 Flash Lite59.9057.0062.80860.00
Gemini 2.5 Flash55.0049.6060.50760.00
Gemini 3 Flash Preview50.9045.1056.50900.00
Lyria 3 Clip Preview34.3032.9035.703440.00
Nano Banana (Gemini 2.5 Flash Image)34.209.1747.201040.00
Gemini 4 Argon16.104.0226.004180.00
Gemini 3.7 Flash8.454.8712.0010800.00
Gemini 3.6 Flash7.977.798.158900.00
Gemini 3.8 Flash7.203.3112.5010300.00
Gemini Flash Latest6.024.597.5711600.00
Gemini 3.5 Flash4.553.855.254370.00
Gemini 2.5 Pro Preview 06-053.493.493.495390.00
Gemini 3.1 Pro Preview Custom Tools2.542.522.566010.00
Gemini 3.1 Pro Preview2.231.572.907760.00
Gemini 2.5 Pro1.711.711.716500.00

Frequently Asked Questions

Which google model is fastest?
Based on recent tests, Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) shows the highest average throughput among tracked google models.
How many recent measurements feed this dashboard?
This provider summary aggregates 218 individual prompts measured across 213 monitoring runs over the past month.