adjustable glasses illustration

eye chart illustration

clipboard illustration

lenses illustration

Phi 4 Multimodal vs.GLM 4.6v

Passed:

Phi 4 Multimodal 49.4% (41/83)

GLM 4.6v 68.0% (51/75)

Average request time:

Phi 4 Multimodal 15.92s

GLM 4.6v 12.37s

Summary

Annotation Understanding

Phi 4 Multimodal 1 / 2

GLM 4.6v 0 / 0

CAPTCHA

Phi 4 Multimodal 0 / 2

GLM 4.6v 2 / 2

Color Identification

Phi 4 Multimodal 0 / 1

GLM 4.6v 0 / 1

Defect Detection

Phi 4 Multimodal 11 / 15

GLM 4.6v 11 / 15

Document Understanding

Phi 4 Multimodal 7 / 10

GLM 4.6v 7 / 8

Localization

Phi 4 Multimodal 0 / 1

GLM 4.6v 1 / 1

OCR

Phi 4 Multimodal 5 / 9

GLM 4.6v 7 / 9

Object Counting

Phi 4 Multimodal 0 / 11

GLM 4.6v 2 / 9

Object Detection

Phi 4 Multimodal 2 / 2

GLM 4.6v 0 / 2

Object Measurement

Phi 4 Multimodal 0 / 1

GLM 4.6v 0 / 1

Object Understanding

Phi 4 Multimodal 5 / 11

GLM 4.6v 8 / 10

Receipt Reading

Phi 4 Multimodal 1 / 1

GLM 4.6v 1 / 1

Sign Understanding

Phi 4 Multimodal 2 / 2

GLM 4.6v 2 / 2

Spatial Relations

Phi 4 Multimodal 7 / 17

GLM 4.6v 9 / 17

Web Action Understanding

Phi 4 Multimodal 2 / 4

GLM 4.6v 4 / 4

Contribute a Prompt

Lightbulb

Have an idea for a prompt? Open a pull request on the project repository!