adjustable glasses illustration

eye chart illustration

clipboard illustration

lenses illustration

Qwen 2.5 VL 7B vs.GLM 4.6v

Passed:

Qwen 2.5 VL 7B 55.6% (45/81)

GLM 4.6v 68.0% (51/75)

Average request time:

Qwen 2.5 VL 7B 45.63s

GLM 4.6v 12.37s

Summary

Annotation Understanding

Qwen 2.5 VL 7B 1 / 2

GLM 4.6v 0 / 0

CAPTCHA

Qwen 2.5 VL 7B 2 / 2

GLM 4.6v 2 / 2

Color Identification

Qwen 2.5 VL 7B 0 / 1

GLM 4.6v 0 / 1

Defect Detection

Qwen 2.5 VL 7B 9 / 15

GLM 4.6v 11 / 15

Document Understanding

Qwen 2.5 VL 7B 8 / 10

GLM 4.6v 7 / 8

Localization

Qwen 2.5 VL 7B 1 / 1

GLM 4.6v 1 / 1

OCR

Qwen 2.5 VL 7B 6 / 9

GLM 4.6v 7 / 9

Object Counting

Qwen 2.5 VL 7B 1 / 9

GLM 4.6v 2 / 9

Object Detection

Qwen 2.5 VL 7B 1 / 2

GLM 4.6v 0 / 2

Object Measurement

Qwen 2.5 VL 7B 0 / 1

GLM 4.6v 0 / 1

Object Understanding

Qwen 2.5 VL 7B 5 / 11

GLM 4.6v 8 / 10

Receipt Reading

Qwen 2.5 VL 7B 0 / 1

GLM 4.6v 1 / 1

Sign Understanding

Qwen 2.5 VL 7B 2 / 2

GLM 4.6v 2 / 2

Spatial Relations

Qwen 2.5 VL 7B 11 / 17

GLM 4.6v 9 / 17

Web Action Understanding

Qwen 2.5 VL 7B 4 / 4

GLM 4.6v 4 / 4

Contribute a Prompt

Lightbulb

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