Phi 4 Multimodal vs.Gemini 1.5 Pro
Passed:
Phi 4 Multimodal 49.4% (41/83)
Gemini 1.5 Pro 63.9% (53/83)
Average request time:
Phi 4 Multimodal 15.92s
Gemini 1.5 Pro 14.78s
Passed:
Phi 4 Multimodal 49.4% (41/83)
Gemini 1.5 Pro 63.9% (53/83)
Average request time:
Phi 4 Multimodal 15.92s
Gemini 1.5 Pro 14.78s
Summary
Annotation Understanding
Phi 4 Multimodal
1 / 2
Gemini 1.5 Pro
1 / 2
CAPTCHA
Phi 4 Multimodal
0 / 2
Gemini 1.5 Pro
2 / 2
Color Identification
Phi 4 Multimodal
0 / 1
Gemini 1.5 Pro
0 / 1
Counting nodes
Phi 4 Multimodal
0 / 1
Gemini 1.5 Pro
0 / 1
Defect Detection
Phi 4 Multimodal
11 / 15
Gemini 1.5 Pro
11 / 15
Document Understanding
Phi 4 Multimodal
7 / 10
Gemini 1.5 Pro
8 / 10
Localization
Phi 4 Multimodal
0 / 1
Gemini 1.5 Pro
1 / 1
OCR
Phi 4 Multimodal
5 / 9
Gemini 1.5 Pro
8 / 9
Object Counting
Phi 4 Multimodal
0 / 10
Gemini 1.5 Pro
2 / 10
Object Detection
Phi 4 Multimodal
2 / 2
Gemini 1.5 Pro
1 / 2
Object Measurement
Phi 4 Multimodal
0 / 2
Gemini 1.5 Pro
0 / 2
Object Understanding
Phi 4 Multimodal
5 / 11
Gemini 1.5 Pro
6 / 11
Receipt Reading
Phi 4 Multimodal
1 / 1
Gemini 1.5 Pro
1 / 1
Sign Understanding
Phi 4 Multimodal
2 / 2
Gemini 1.5 Pro
2 / 2
Spatial Relations
Phi 4 Multimodal
7 / 17
Gemini 1.5 Pro
12 / 17
Web Action Understanding
Phi 4 Multimodal
2 / 4
Gemini 1.5 Pro
4 / 4
Contribute a Prompt
Have an idea for a prompt? Open a pull request on the project repository!