Go
gemini-3.5-flash Benchmark & Insights
Google Gemini API
Updated Jun 6, 2026 All models
Sample size
18 runs
in window
Accuracy
95.0%
consensus match · 20d
Confidence
94%
over 20 runs
Window end
Jun 6, 2026
most recent run
Input price
$1.50/MTok
prompt tokens
Output price
$9.00/MTok
completion tokens
Model insights
- 01 One cautious "medium" overcall in 18 days — clean so far, but the sample is still small enough to keep judgment provisional.
- 02 At $1.50/$9.00 it costs 6x the flash-lite line without showing an accuracy gain yet.
Notes
A new stable version of Gemini 3.5 Flash