adjustable glasses illustration eye chart illustration clipboard illustration lenses illustration

GPT-5 vs.Phi 4 Multimodal

Passed:
GPT-5 75.9% (63/83)
Phi 4 Multimodal 49.4% (41/83)
Average request time:
GPT-5 25.28s
Phi 4 Multimodal 15.92s

Summary

Annotation Understanding
GPT-5 1 / 2
Phi 4 Multimodal 1 / 2
CAPTCHA
GPT-5 0 / 2
Phi 4 Multimodal 0 / 2
Color Identification
GPT-5 1 / 1
Phi 4 Multimodal 0 / 1
Counting nodes
GPT-5 0 / 1
Phi 4 Multimodal 0 / 1
Defect Detection
GPT-5 13 / 15
Phi 4 Multimodal 11 / 15
Document Understanding
GPT-5 8 / 10
Phi 4 Multimodal 7 / 10
Localization
GPT-5 0 / 1
Phi 4 Multimodal 0 / 1
OCR
GPT-5 9 / 9
Phi 4 Multimodal 5 / 9
Object Counting
GPT-5 4 / 10
Phi 4 Multimodal 0 / 10
Object Detection
GPT-5 2 / 2
Phi 4 Multimodal 2 / 2
Object Measurement
GPT-5 0 / 2
Phi 4 Multimodal 0 / 2
Object Understanding
GPT-5 9 / 11
Phi 4 Multimodal 5 / 11
Receipt Reading
GPT-5 1 / 1
Phi 4 Multimodal 1 / 1
Sign Understanding
GPT-5 2 / 2
Phi 4 Multimodal 2 / 2
Spatial Relations
GPT-5 15 / 17
Phi 4 Multimodal 7 / 17
Web Action Understanding
GPT-5 4 / 4
Phi 4 Multimodal 2 / 4

Contribute a Prompt