Gemini 3.1 Pro vs.Gemini 2.0 Flash Lite
Passed:
Gemini 3.1 Pro 81.7% (67/82)
Gemini 2.0 Flash Lite 62.2% (51/82)
Average request time:
Gemini 3.1 Pro 12.43s
Gemini 2.0 Flash Lite 5.43s
Passed:
Gemini 3.1 Pro 81.7% (67/82)
Gemini 2.0 Flash Lite 62.2% (51/82)
Average request time:
Gemini 3.1 Pro 12.43s
Gemini 2.0 Flash Lite 5.43s
Summary
Annotation Understanding
Gemini 3.1 Pro
2 / 2
Gemini 2.0 Flash Lite
0 / 2
CAPTCHA
Gemini 3.1 Pro
2 / 2
Gemini 2.0 Flash Lite
0 / 2
Color Identification
Gemini 3.1 Pro
1 / 1
Gemini 2.0 Flash Lite
0 / 1
Defect Detection
Gemini 3.1 Pro
11 / 15
Gemini 2.0 Flash Lite
10 / 15
Document Understanding
Gemini 3.1 Pro
8 / 10
Gemini 2.0 Flash Lite
7 / 10
Localization
Gemini 3.1 Pro
1 / 1
Gemini 2.0 Flash Lite
0 / 1
OCR
Gemini 3.1 Pro
9 / 9
Gemini 2.0 Flash Lite
8 / 9
Object Counting
Gemini 3.1 Pro
5 / 11
Gemini 2.0 Flash Lite
3 / 11
Object Detection
Gemini 3.1 Pro
2 / 2
Gemini 2.0 Flash Lite
1 / 2
Object Measurement
Gemini 3.1 Pro
1 / 1
Gemini 2.0 Flash Lite
0 / 1
Object Understanding
Gemini 3.1 Pro
11 / 11
Gemini 2.0 Flash Lite
6 / 11
Receipt Reading
Gemini 3.1 Pro
1 / 1
Gemini 2.0 Flash Lite
1 / 1
Sign Understanding
Gemini 3.1 Pro
2 / 2
Gemini 2.0 Flash Lite
2 / 2
Spatial Relations
Gemini 3.1 Pro
12 / 17
Gemini 2.0 Flash Lite
12 / 17
Web Action Understanding
Gemini 3.1 Pro
4 / 4
Gemini 2.0 Flash Lite
4 / 4
Contribute a Prompt
Have an idea for a prompt? Open a pull request on the project repository!