Phi 4 Multimodal vs.Kimi k2.5
Passed:
Phi 4 Multimodal 49.4% (41/83)
Kimi k2.5 73.5% (50/68)
Average request time:
Phi 4 Multimodal 15.92s
Kimi k2.5 44.70s
Passed:
Phi 4 Multimodal 49.4% (41/83)
Kimi k2.5 73.5% (50/68)
Average request time:
Phi 4 Multimodal 15.92s
Kimi k2.5 44.70s
Summary
Annotation Understanding
Phi 4 Multimodal
1 / 2
Kimi k2.5
1 / 1
CAPTCHA
Phi 4 Multimodal
0 / 2
Kimi k2.5
2 / 2
Color Identification
Phi 4 Multimodal
0 / 1
Kimi k2.5
1 / 1
Defect Detection
Phi 4 Multimodal
11 / 15
Kimi k2.5
8 / 14
Document Understanding
Phi 4 Multimodal
7 / 10
Kimi k2.5
8 / 8
Localization
Phi 4 Multimodal
0 / 1
Kimi k2.5
1 / 1
OCR
Phi 4 Multimodal
5 / 9
Kimi k2.5
7 / 9
Object Counting
Phi 4 Multimodal
0 / 11
Kimi k2.5
1 / 3
Object Detection
Phi 4 Multimodal
2 / 2
Kimi k2.5
1 / 2
Object Measurement
Phi 4 Multimodal
0 / 1
Kimi k2.5
0 / 1
Object Understanding
Phi 4 Multimodal
5 / 11
Kimi k2.5
9 / 11
Receipt Reading
Phi 4 Multimodal
1 / 1
Kimi k2.5
1 / 1
Sign Understanding
Phi 4 Multimodal
2 / 2
Kimi k2.5
2 / 2
Spatial Relations
Phi 4 Multimodal
7 / 17
Kimi k2.5
12 / 15
Web Action Understanding
Phi 4 Multimodal
2 / 4
Kimi k2.5
3 / 4
Contribute a Prompt
Have an idea for a prompt? Open a pull request on the project repository!