GLM 4.6v vs.Grok 4
Passed:
GLM 4.6v 68.0% (51/75)
Grok 4 56.1% (46/82)
Average request time:
GLM 4.6v 12.37s
Grok 4 79.45s
Passed:
GLM 4.6v 68.0% (51/75)
Grok 4 56.1% (46/82)
Average request time:
GLM 4.6v 12.37s
Grok 4 79.45s
Summary
Annotation Understanding
GLM 4.6v
0 / 0
Grok 4
1 / 2
CAPTCHA
GLM 4.6v
2 / 2
Grok 4
2 / 2
Color Identification
GLM 4.6v
0 / 1
Grok 4
1 / 1
Defect Detection
GLM 4.6v
11 / 15
Grok 4
12 / 15
Document Understanding
GLM 4.6v
7 / 8
Grok 4
4 / 10
Localization
GLM 4.6v
1 / 1
Grok 4
0 / 1
OCR
GLM 4.6v
7 / 9
Grok 4
6 / 9
Object Counting
GLM 4.6v
2 / 9
Grok 4
1 / 11
Object Detection
GLM 4.6v
0 / 2
Grok 4
2 / 2
Object Measurement
GLM 4.6v
0 / 1
Grok 4
0 / 1
Object Understanding
GLM 4.6v
8 / 10
Grok 4
7 / 11
Receipt Reading
GLM 4.6v
1 / 1
Grok 4
0 / 1
Sign Understanding
GLM 4.6v
2 / 2
Grok 4
2 / 2
Spatial Relations
GLM 4.6v
9 / 17
Grok 4
10 / 17
Web Action Understanding
GLM 4.6v
4 / 4
Grok 4
2 / 4
Contribute a Prompt
Have an idea for a prompt? Open a pull request on the project repository!