Gemini 2.5 Flash vs.Gemini 3.1 Pro (Tools)
Passed:
Gemini 2.5 Flash 61.0% (50/82)
Gemini 3.1 Pro (Tools) 84.1% (69/82)
Average request time:
Gemini 2.5 Flash 20.76s
Gemini 3.1 Pro (Tools) 26.26s
Passed:
Gemini 2.5 Flash 61.0% (50/82)
Gemini 3.1 Pro (Tools) 84.1% (69/82)
Average request time:
Gemini 2.5 Flash 20.76s
Gemini 3.1 Pro (Tools) 26.26s
Summary
Annotation Understanding
Gemini 2.5 Flash
0 / 2
Gemini 3.1 Pro (Tools)
1 / 2
CAPTCHA
Gemini 2.5 Flash
2 / 2
Gemini 3.1 Pro (Tools)
2 / 2
Color Identification
Gemini 2.5 Flash
0 / 1
Gemini 3.1 Pro (Tools)
1 / 1
Defect Detection
Gemini 2.5 Flash
9 / 15
Gemini 3.1 Pro (Tools)
12 / 15
Document Understanding
Gemini 2.5 Flash
8 / 10
Gemini 3.1 Pro (Tools)
9 / 10
Localization
Gemini 2.5 Flash
0 / 1
Gemini 3.1 Pro (Tools)
1 / 1
OCR
Gemini 2.5 Flash
9 / 9
Gemini 3.1 Pro (Tools)
9 / 9
Object Counting
Gemini 2.5 Flash
1 / 11
Gemini 3.1 Pro (Tools)
5 / 11
Object Detection
Gemini 2.5 Flash
0 / 2
Gemini 3.1 Pro (Tools)
2 / 2
Object Measurement
Gemini 2.5 Flash
0 / 1
Gemini 3.1 Pro (Tools)
1 / 1
Object Understanding
Gemini 2.5 Flash
9 / 11
Gemini 3.1 Pro (Tools)
10 / 11
Receipt Reading
Gemini 2.5 Flash
1 / 1
Gemini 3.1 Pro (Tools)
1 / 1
Sign Understanding
Gemini 2.5 Flash
2 / 2
Gemini 3.1 Pro (Tools)
2 / 2
Spatial Relations
Gemini 2.5 Flash
11 / 17
Gemini 3.1 Pro (Tools)
14 / 17
Web Action Understanding
Gemini 2.5 Flash
4 / 4
Gemini 3.1 Pro (Tools)
4 / 4
Contribute a Prompt
Have an idea for a prompt? Open a pull request on the project repository!