ChatGPT-4o vs.Gemini 2.0 Flash
Passed:
ChatGPT-4o 78.0% (64/82)
Gemini 2.0 Flash 67.1% (55/82)
Average request time:
ChatGPT-4o 13.60s
Gemini 2.0 Flash 9.11s
Passed:
ChatGPT-4o 78.0% (64/82)
Gemini 2.0 Flash 67.1% (55/82)
Average request time:
ChatGPT-4o 13.60s
Gemini 2.0 Flash 9.11s
Summary
Annotation Understanding
ChatGPT-4o
1 / 2
Gemini 2.0 Flash
2 / 2
CAPTCHA
ChatGPT-4o
2 / 2
Gemini 2.0 Flash
2 / 2
Color Identification
ChatGPT-4o
1 / 1
Gemini 2.0 Flash
1 / 1
Counting nodes
ChatGPT-4o
0 / 1
Gemini 2.0 Flash
0 / 1
Defect Detection
ChatGPT-4o
14 / 15
Gemini 2.0 Flash
10 / 15
Document Understanding
ChatGPT-4o
5 / 10
Gemini 2.0 Flash
6 / 10
Localization
ChatGPT-4o
1 / 1
Gemini 2.0 Flash
1 / 1
OCR
ChatGPT-4o
9 / 9
Gemini 2.0 Flash
7 / 9
Object Counting
ChatGPT-4o
2 / 10
Gemini 2.0 Flash
3 / 10
Object Detection
ChatGPT-4o
2 / 2
Gemini 2.0 Flash
1 / 2
Object Measurement
ChatGPT-4o
1 / 2
Gemini 2.0 Flash
0 / 2
Object Understanding
ChatGPT-4o
9 / 10
Gemini 2.0 Flash
8 / 10
Receipt Reading
ChatGPT-4o
1 / 1
Gemini 2.0 Flash
1 / 1
Sign Understanding
ChatGPT-4o
2 / 2
Gemini 2.0 Flash
2 / 2
Spatial Relations
ChatGPT-4o
16 / 17
Gemini 2.0 Flash
13 / 17
Web Action Understanding
ChatGPT-4o
4 / 4
Gemini 2.0 Flash
4 / 4
Contribute a Prompt
Have an idea for a prompt? Open a pull request on the project repository!