ChatGPT-4o vs.Gemma 3 27b
Passed:
ChatGPT-4o 78.0% (64/82)
Gemma 3 27b 64.6% (53/82)
Average request time:
ChatGPT-4o 13.60s
Gemma 3 27b 11.02s
Passed:
ChatGPT-4o 78.0% (64/82)
Gemma 3 27b 64.6% (53/82)
Average request time:
ChatGPT-4o 13.60s
Gemma 3 27b 11.02s
Summary
Annotation Understanding
ChatGPT-4o
1 / 2
Gemma 3 27b
0 / 2
CAPTCHA
ChatGPT-4o
2 / 2
Gemma 3 27b
2 / 2
Color Identification
ChatGPT-4o
1 / 1
Gemma 3 27b
1 / 1
Counting nodes
ChatGPT-4o
0 / 1
Gemma 3 27b
0 / 1
Defect Detection
ChatGPT-4o
14 / 15
Gemma 3 27b
12 / 15
Document Understanding
ChatGPT-4o
5 / 9
Gemma 3 27b
5 / 9
Find an author
ChatGPT-4o
0 / 1
Gemma 3 27b
0 / 1
Localization
ChatGPT-4o
1 / 1
Gemma 3 27b
1 / 1
OCR
ChatGPT-4o
9 / 9
Gemma 3 27b
6 / 9
Object Counting
ChatGPT-4o
2 / 10
Gemma 3 27b
2 / 10
Object Detection
ChatGPT-4o
2 / 2
Gemma 3 27b
2 / 2
Object Measurement
ChatGPT-4o
1 / 2
Gemma 3 27b
0 / 2
Object Understanding
ChatGPT-4o
9 / 10
Gemma 3 27b
9 / 10
Receipt Reading
ChatGPT-4o
1 / 1
Gemma 3 27b
1 / 1
Sign Understanding
ChatGPT-4o
2 / 2
Gemma 3 27b
2 / 2
Spatial Relations
ChatGPT-4o
16 / 17
Gemma 3 27b
10 / 17
Web Action Understanding
ChatGPT-4o
4 / 4
Gemma 3 27b
4 / 4
Contribute a Prompt
Have an idea for a prompt? Open a pull request on the project repository!