Gemini 3.1 Pro vs.GLM 4.6v
Passed:
Gemini 3.1 Pro 81.7% (67/82)
GLM 4.6v 68.0% (51/75)
Average request time:
Gemini 3.1 Pro 12.43s
GLM 4.6v 12.37s
Passed:
Gemini 3.1 Pro 81.7% (67/82)
GLM 4.6v 68.0% (51/75)
Average request time:
Gemini 3.1 Pro 12.43s
GLM 4.6v 12.37s
Summary
Annotation Understanding
Gemini 3.1 Pro
2 / 2
GLM 4.6v
0 / 0
CAPTCHA
Gemini 3.1 Pro
2 / 2
GLM 4.6v
2 / 2
Color Identification
Gemini 3.1 Pro
1 / 1
GLM 4.6v
0 / 1
Defect Detection
Gemini 3.1 Pro
11 / 15
GLM 4.6v
11 / 15
Document Understanding
Gemini 3.1 Pro
8 / 10
GLM 4.6v
7 / 8
Localization
Gemini 3.1 Pro
1 / 1
GLM 4.6v
1 / 1
OCR
Gemini 3.1 Pro
9 / 9
GLM 4.6v
7 / 9
Object Counting
Gemini 3.1 Pro
5 / 11
GLM 4.6v
2 / 9
Object Detection
Gemini 3.1 Pro
2 / 2
GLM 4.6v
0 / 2
Object Measurement
Gemini 3.1 Pro
1 / 1
GLM 4.6v
0 / 1
Object Understanding
Gemini 3.1 Pro
11 / 11
GLM 4.6v
8 / 10
Receipt Reading
Gemini 3.1 Pro
1 / 1
GLM 4.6v
1 / 1
Sign Understanding
Gemini 3.1 Pro
2 / 2
GLM 4.6v
2 / 2
Spatial Relations
Gemini 3.1 Pro
12 / 17
GLM 4.6v
9 / 17
Web Action Understanding
Gemini 3.1 Pro
4 / 4
GLM 4.6v
4 / 4
Contribute a Prompt
Have an idea for a prompt? Open a pull request on the project repository!