Qwen 3.6 Plus vs.GLM 4.6v
Passed:
Qwen 3.6 Plus 74.4% (61/82)
GLM 4.6v 68.0% (51/75)
Average request time:
Qwen 3.6 Plus 81.82s
GLM 4.6v 12.37s
Passed:
Qwen 3.6 Plus 74.4% (61/82)
GLM 4.6v 68.0% (51/75)
Average request time:
Qwen 3.6 Plus 81.82s
GLM 4.6v 12.37s
Summary
Annotation Understanding
Qwen 3.6 Plus
1 / 2
GLM 4.6v
0 / 0
CAPTCHA
Qwen 3.6 Plus
2 / 2
GLM 4.6v
2 / 2
Color Identification
Qwen 3.6 Plus
1 / 1
GLM 4.6v
0 / 1
Defect Detection
Qwen 3.6 Plus
11 / 15
GLM 4.6v
11 / 15
Document Understanding
Qwen 3.6 Plus
9 / 10
GLM 4.6v
7 / 8
Localization
Qwen 3.6 Plus
0 / 1
GLM 4.6v
1 / 1
OCR
Qwen 3.6 Plus
7 / 9
GLM 4.6v
7 / 9
Object Counting
Qwen 3.6 Plus
4 / 11
GLM 4.6v
2 / 9
Object Detection
Qwen 3.6 Plus
1 / 2
GLM 4.6v
0 / 2
Object Measurement
Qwen 3.6 Plus
1 / 1
GLM 4.6v
0 / 1
Object Understanding
Qwen 3.6 Plus
10 / 11
GLM 4.6v
8 / 10
Receipt Reading
Qwen 3.6 Plus
1 / 1
GLM 4.6v
1 / 1
Sign Understanding
Qwen 3.6 Plus
2 / 2
GLM 4.6v
2 / 2
Spatial Relations
Qwen 3.6 Plus
14 / 17
GLM 4.6v
9 / 17
Web Action Understanding
Qwen 3.6 Plus
4 / 4
GLM 4.6v
4 / 4
Contribute a Prompt
Have an idea for a prompt? Open a pull request on the project repository!