Mistral Small 3.1 24B vs.Phi 4 Multimodal
Passed:
Mistral Small 3.1 24B 44.6% (37/83)
Phi 4 Multimodal 49.4% (41/83)
Average request time:
Mistral Small 3.1 24B 15.16s
Phi 4 Multimodal 15.92s
Passed:
Mistral Small 3.1 24B 44.6% (37/83)
Phi 4 Multimodal 49.4% (41/83)
Average request time:
Mistral Small 3.1 24B 15.16s
Phi 4 Multimodal 15.92s
Summary
Annotation Understanding
Mistral Small 3.1 24B
0 / 2
Phi 4 Multimodal
1 / 2
CAPTCHA
Mistral Small 3.1 24B
2 / 2
Phi 4 Multimodal
0 / 2
Color Identification
Mistral Small 3.1 24B
1 / 1
Phi 4 Multimodal
0 / 1
Counting nodes
Mistral Small 3.1 24B
0 / 1
Phi 4 Multimodal
0 / 1
Defect Detection
Mistral Small 3.1 24B
8 / 15
Phi 4 Multimodal
11 / 15
Document Understanding
Mistral Small 3.1 24B
5 / 10
Phi 4 Multimodal
7 / 10
Localization
Mistral Small 3.1 24B
0 / 1
Phi 4 Multimodal
0 / 1
OCR
Mistral Small 3.1 24B
7 / 9
Phi 4 Multimodal
5 / 9
Object Counting
Mistral Small 3.1 24B
0 / 10
Phi 4 Multimodal
0 / 10
Object Detection
Mistral Small 3.1 24B
1 / 2
Phi 4 Multimodal
2 / 2
Object Measurement
Mistral Small 3.1 24B
0 / 2
Phi 4 Multimodal
0 / 2
Object Understanding
Mistral Small 3.1 24B
4 / 11
Phi 4 Multimodal
5 / 11
Receipt Reading
Mistral Small 3.1 24B
1 / 1
Phi 4 Multimodal
1 / 1
Sign Understanding
Mistral Small 3.1 24B
0 / 2
Phi 4 Multimodal
2 / 2
Spatial Relations
Mistral Small 3.1 24B
6 / 17
Phi 4 Multimodal
7 / 17
Web Action Understanding
Mistral Small 3.1 24B
4 / 4
Phi 4 Multimodal
2 / 4
Contribute a Prompt
Have an idea for a prompt? Open a pull request on the project repository!