Gemma 3 27b vs.Mistral Medium 3
Passed:
Gemma 3 27b 64.6% (53/82)
Mistral Medium 3 61.0% (50/82)
Average request time:
Gemma 3 27b 11.02s
Mistral Medium 3 16.63s
Passed:
Gemma 3 27b 64.6% (53/82)
Mistral Medium 3 61.0% (50/82)
Average request time:
Gemma 3 27b 11.02s
Mistral Medium 3 16.63s
Summary
Annotation Understanding
Gemma 3 27b
0 / 2
Mistral Medium 3
0 / 2
CAPTCHA
Gemma 3 27b
2 / 2
Mistral Medium 3
2 / 2
Color Identification
Gemma 3 27b
1 / 1
Mistral Medium 3
0 / 1
Counting nodes
Gemma 3 27b
0 / 1
Mistral Medium 3
0 / 1
Defect Detection
Gemma 3 27b
12 / 15
Mistral Medium 3
10 / 15
Document Understanding
Gemma 3 27b
5 / 10
Mistral Medium 3
5 / 10
Localization
Gemma 3 27b
1 / 1
Mistral Medium 3
1 / 1
OCR
Gemma 3 27b
6 / 9
Mistral Medium 3
9 / 9
Object Counting
Gemma 3 27b
2 / 10
Mistral Medium 3
1 / 10
Object Detection
Gemma 3 27b
2 / 2
Mistral Medium 3
2 / 2
Object Measurement
Gemma 3 27b
0 / 2
Mistral Medium 3
0 / 2
Object Understanding
Gemma 3 27b
9 / 10
Mistral Medium 3
8 / 10
Receipt Reading
Gemma 3 27b
1 / 1
Mistral Medium 3
1 / 1
Sign Understanding
Gemma 3 27b
2 / 2
Mistral Medium 3
2 / 2
Spatial Relations
Gemma 3 27b
10 / 17
Mistral Medium 3
8 / 17
Web Action Understanding
Gemma 3 27b
4 / 4
Mistral Medium 3
4 / 4
Contribute a Prompt
Have an idea for a prompt? Open a pull request on the project repository!