adjustable glasses illustration

eye chart illustration

clipboard illustration

lenses illustration

Gemma 3 27b vs.Phi 4 Multimodal

Passed:

Gemma 3 27b 63.0% (51/81)

Phi 4 Multimodal 49.4% (41/83)

Average request time:

Gemma 3 27b 30.87s

Phi 4 Multimodal 15.92s

Summary

Annotation Understanding

Gemma 3 27b 0 / 2

Phi 4 Multimodal 1 / 2

CAPTCHA

Gemma 3 27b 2 / 2

Phi 4 Multimodal 0 / 2

Color Identification

Gemma 3 27b 0 / 1

Phi 4 Multimodal 0 / 1

Counting nodes

Gemma 3 27b 0 / 0

Phi 4 Multimodal 0 / 1

Defect Detection

Gemma 3 27b 9 / 15

Phi 4 Multimodal 11 / 15

Document Understanding

Gemma 3 27b 8 / 10

Phi 4 Multimodal 7 / 10

Localization

Gemma 3 27b 1 / 1

Phi 4 Multimodal 0 / 1

OCR

Gemma 3 27b 6 / 9

Phi 4 Multimodal 5 / 9

Object Counting

Gemma 3 27b 1 / 9

Phi 4 Multimodal 0 / 10

Object Detection

Gemma 3 27b 2 / 2

Phi 4 Multimodal 2 / 2

Object Measurement

Gemma 3 27b 0 / 2

Phi 4 Multimodal 0 / 2

Object Understanding

Gemma 3 27b 8 / 11

Phi 4 Multimodal 5 / 11

Receipt Reading

Gemma 3 27b 1 / 1

Phi 4 Multimodal 1 / 1

Sign Understanding

Gemma 3 27b 2 / 2

Phi 4 Multimodal 2 / 2

Spatial Relations

Gemma 3 27b 11 / 17

Phi 4 Multimodal 7 / 17

Web Action Understanding

Gemma 3 27b 4 / 4

Phi 4 Multimodal 2 / 4

Contribute a Prompt

Lightbulb

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