GLM 4.6v vs.Qwen 3.5 122B (A10B)
Passed:
GLM 4.6v 68.0% (51/75)
Qwen 3.5 122B (A10B) 78.0% (64/82)
Average request time:
GLM 4.6v 12.37s
Qwen 3.5 122B (A10B) 1.54s
Passed:
GLM 4.6v 68.0% (51/75)
Qwen 3.5 122B (A10B) 78.0% (64/82)
Average request time:
GLM 4.6v 12.37s
Qwen 3.5 122B (A10B) 1.54s
Summary
Annotation Understanding
GLM 4.6v
0 / 0
Qwen 3.5 122B (A10B)
1 / 2
CAPTCHA
GLM 4.6v
2 / 2
Qwen 3.5 122B (A10B)
2 / 2
Color Identification
GLM 4.6v
0 / 1
Qwen 3.5 122B (A10B)
1 / 1
Defect Detection
GLM 4.6v
11 / 15
Qwen 3.5 122B (A10B)
13 / 15
Document Understanding
GLM 4.6v
7 / 8
Qwen 3.5 122B (A10B)
9 / 10
Localization
GLM 4.6v
1 / 1
Qwen 3.5 122B (A10B)
1 / 1
OCR
GLM 4.6v
7 / 9
Qwen 3.5 122B (A10B)
7 / 9
Object Counting
GLM 4.6v
2 / 9
Qwen 3.5 122B (A10B)
5 / 11
Object Detection
GLM 4.6v
0 / 2
Qwen 3.5 122B (A10B)
2 / 2
Object Measurement
GLM 4.6v
0 / 1
Qwen 3.5 122B (A10B)
1 / 1
Object Understanding
GLM 4.6v
8 / 10
Qwen 3.5 122B (A10B)
8 / 11
Receipt Reading
GLM 4.6v
1 / 1
Qwen 3.5 122B (A10B)
1 / 1
Sign Understanding
GLM 4.6v
2 / 2
Qwen 3.5 122B (A10B)
2 / 2
Spatial Relations
GLM 4.6v
9 / 17
Qwen 3.5 122B (A10B)
14 / 17
Web Action Understanding
GLM 4.6v
4 / 4
Qwen 3.5 122B (A10B)
4 / 4
Contribute a Prompt
Have an idea for a prompt? Open a pull request on the project repository!