Gemma 3 4B vs.Molmo2 8B
Passed:
Gemma 3 4B 42.2% (35/83)
Molmo2 8B 53.7% (44/82)
Average request time:
Gemma 3 4B 15.86s
Molmo2 8B 1.16s
Passed:
Gemma 3 4B 42.2% (35/83)
Molmo2 8B 53.7% (44/82)
Average request time:
Gemma 3 4B 15.86s
Molmo2 8B 1.16s
Summary
Annotation Understanding
Gemma 3 4B
0 / 2
Molmo2 8B
0 / 2
CAPTCHA
Gemma 3 4B
2 / 2
Molmo2 8B
0 / 2
Color Identification
Gemma 3 4B
0 / 1
Molmo2 8B
1 / 1
Defect Detection
Gemma 3 4B
9 / 15
Molmo2 8B
10 / 15
Document Understanding
Gemma 3 4B
6 / 10
Molmo2 8B
6 / 10
Localization
Gemma 3 4B
0 / 1
Molmo2 8B
1 / 1
OCR
Gemma 3 4B
6 / 9
Molmo2 8B
6 / 9
Object Counting
Gemma 3 4B
0 / 11
Molmo2 8B
1 / 11
Object Detection
Gemma 3 4B
2 / 2
Molmo2 8B
1 / 2
Object Measurement
Gemma 3 4B
0 / 1
Molmo2 8B
0 / 1
Object Understanding
Gemma 3 4B
5 / 11
Molmo2 8B
7 / 11
Receipt Reading
Gemma 3 4B
0 / 1
Molmo2 8B
0 / 1
Sign Understanding
Gemma 3 4B
2 / 2
Molmo2 8B
2 / 2
Spatial Relations
Gemma 3 4B
4 / 17
Molmo2 8B
9 / 17
Web Action Understanding
Gemma 3 4B
2 / 4
Molmo2 8B
4 / 4
Contribute a Prompt
Have an idea for a prompt? Open a pull request on the project repository!