GPT-4.1 vs.GLM 4.6v
Passed:
GPT-4.1 70.7% (58/82)
GLM 4.6v 68.0% (51/75)
Average request time:
GPT-4.1 12.46s
GLM 4.6v 12.37s
Passed:
GPT-4.1 70.7% (58/82)
GLM 4.6v 68.0% (51/75)
Average request time:
GPT-4.1 12.46s
GLM 4.6v 12.37s
Summary
Annotation Understanding
GPT-4.1
1 / 2
GLM 4.6v
0 / 0
CAPTCHA
GPT-4.1
0 / 2
GLM 4.6v
2 / 2
Color Identification
GPT-4.1
0 / 1
GLM 4.6v
0 / 1
Defect Detection
GPT-4.1
12 / 15
GLM 4.6v
11 / 15
Document Understanding
GPT-4.1
7 / 10
GLM 4.6v
7 / 8
Localization
GPT-4.1
1 / 1
GLM 4.6v
1 / 1
OCR
GPT-4.1
9 / 9
GLM 4.6v
7 / 9
Object Counting
GPT-4.1
2 / 11
GLM 4.6v
2 / 9
Object Detection
GPT-4.1
2 / 2
GLM 4.6v
0 / 2
Object Measurement
GPT-4.1
0 / 1
GLM 4.6v
0 / 1
Object Understanding
GPT-4.1
7 / 11
GLM 4.6v
8 / 10
Receipt Reading
GPT-4.1
1 / 1
GLM 4.6v
1 / 1
Sign Understanding
GPT-4.1
2 / 2
GLM 4.6v
2 / 2
Spatial Relations
GPT-4.1
15 / 17
GLM 4.6v
9 / 17
Web Action Understanding
GPT-4.1
4 / 4
GLM 4.6v
4 / 4
Contribute a Prompt
Have an idea for a prompt? Open a pull request on the project repository!