Claude 3.7 Sonnet vs.GLM 4.6v
Passed:
Claude 3.7 Sonnet 63.9% (53/83)
GLM 4.6v 68.0% (51/75)
Average request time:
Claude 3.7 Sonnet 13.98s
GLM 4.6v 12.37s
Passed:
Claude 3.7 Sonnet 63.9% (53/83)
GLM 4.6v 68.0% (51/75)
Average request time:
Claude 3.7 Sonnet 13.98s
GLM 4.6v 12.37s
Summary
Annotation Understanding
Claude 3.7 Sonnet
0 / 2
GLM 4.6v
0 / 0
CAPTCHA
Claude 3.7 Sonnet
2 / 2
GLM 4.6v
2 / 2
Color Identification
Claude 3.7 Sonnet
1 / 1
GLM 4.6v
0 / 1
Defect Detection
Claude 3.7 Sonnet
10 / 15
GLM 4.6v
11 / 15
Document Understanding
Claude 3.7 Sonnet
9 / 10
GLM 4.6v
7 / 8
Localization
Claude 3.7 Sonnet
1 / 1
GLM 4.6v
1 / 1
OCR
Claude 3.7 Sonnet
7 / 9
GLM 4.6v
7 / 9
Object Counting
Claude 3.7 Sonnet
2 / 11
GLM 4.6v
2 / 9
Object Detection
Claude 3.7 Sonnet
2 / 2
GLM 4.6v
0 / 2
Object Measurement
Claude 3.7 Sonnet
0 / 1
GLM 4.6v
0 / 1
Object Understanding
Claude 3.7 Sonnet
7 / 11
GLM 4.6v
8 / 10
Receipt Reading
Claude 3.7 Sonnet
1 / 1
GLM 4.6v
1 / 1
Sign Understanding
Claude 3.7 Sonnet
2 / 2
GLM 4.6v
2 / 2
Spatial Relations
Claude 3.7 Sonnet
9 / 17
GLM 4.6v
9 / 17
Web Action Understanding
Claude 3.7 Sonnet
4 / 4
GLM 4.6v
4 / 4
Contribute a Prompt
Have an idea for a prompt? Open a pull request on the project repository!