Gemma 3 27b vs.Mistral Medium 3
Passed:
Gemma 3 27b 63.0% (51/81)
Mistral Medium 3 68.7% (57/83)
Average request time:
Gemma 3 27b 30.87s
Mistral Medium 3 13.13s
Passed:
Gemma 3 27b 63.0% (51/81)
Mistral Medium 3 68.7% (57/83)
Average request time:
Gemma 3 27b 30.87s
Mistral Medium 3 13.13s
Summary
Annotation Understanding
Gemma 3 27b
0 / 2
Mistral Medium 3
1 / 2
CAPTCHA
Gemma 3 27b
2 / 2
Mistral Medium 3
2 / 2
Color Identification
Gemma 3 27b
0 / 1
Mistral Medium 3
0 / 1
Counting nodes
Gemma 3 27b
0 / 0
Mistral Medium 3
0 / 1
Defect Detection
Gemma 3 27b
9 / 15
Mistral Medium 3
12 / 15
Document Understanding
Gemma 3 27b
8 / 10
Mistral Medium 3
8 / 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
1 / 9
Mistral Medium 3
2 / 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
8 / 11
Mistral Medium 3
9 / 11
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
11 / 17
Mistral Medium 3
7 / 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!