Gemini 2.5 Pro vs.Gemma 4 31B
Passed:
Gemini 2.5 Pro 74.4% (61/82)
Gemma 4 31B 72.2% (39/54)
Average request time:
Gemini 2.5 Pro 9.95s
Gemma 4 31B 15.30s
Passed:
Gemini 2.5 Pro 74.4% (61/82)
Gemma 4 31B 72.2% (39/54)
Average request time:
Gemini 2.5 Pro 9.95s
Gemma 4 31B 15.30s
Summary
Annotation Understanding
Gemini 2.5 Pro
1 / 2
Gemma 4 31B
0 / 1
CAPTCHA
Gemini 2.5 Pro
2 / 2
Gemma 4 31B
2 / 2
Color Identification
Gemini 2.5 Pro
0 / 1
Gemma 4 31B
0 / 0
Defect Detection
Gemini 2.5 Pro
10 / 15
Gemma 4 31B
6 / 8
Document Understanding
Gemini 2.5 Pro
9 / 10
Gemma 4 31B
7 / 7
Localization
Gemini 2.5 Pro
1 / 1
Gemma 4 31B
0 / 1
OCR
Gemini 2.5 Pro
9 / 9
Gemma 4 31B
4 / 4
Object Counting
Gemini 2.5 Pro
4 / 11
Gemma 4 31B
2 / 8
Object Detection
Gemini 2.5 Pro
2 / 2
Gemma 4 31B
1 / 2
Object Measurement
Gemini 2.5 Pro
0 / 1
Gemma 4 31B
0 / 0
Object Understanding
Gemini 2.5 Pro
8 / 11
Gemma 4 31B
4 / 7
Receipt Reading
Gemini 2.5 Pro
1 / 1
Gemma 4 31B
1 / 1
Sign Understanding
Gemini 2.5 Pro
2 / 2
Gemma 4 31B
1 / 1
Spatial Relations
Gemini 2.5 Pro
14 / 17
Gemma 4 31B
10 / 13
Web Action Understanding
Gemini 2.5 Pro
4 / 4
Gemma 4 31B
4 / 4
Contribute a Prompt
Have an idea for a prompt? Open a pull request on the project repository!