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