GPT-4.1 Nano vs.Gemma 3 27b
Passed:
GPT-4.1 Nano 46.3% (38/82)
Gemma 3 27b 64.6% (53/82)
Average request time:
GPT-4.1 Nano 13.58s
Gemma 3 27b 11.02s
Passed:
GPT-4.1 Nano 46.3% (38/82)
Gemma 3 27b 64.6% (53/82)
Average request time:
GPT-4.1 Nano 13.58s
Gemma 3 27b 11.02s
Summary
Annotation Understanding
GPT-4.1 Nano
0 / 2
Gemma 3 27b
0 / 2
CAPTCHA
GPT-4.1 Nano
0 / 2
Gemma 3 27b
2 / 2
Color Identification
GPT-4.1 Nano
1 / 1
Gemma 3 27b
1 / 1
Counting nodes
GPT-4.1 Nano
0 / 1
Gemma 3 27b
0 / 1
Defect Detection
GPT-4.1 Nano
6 / 15
Gemma 3 27b
12 / 15
Document Understanding
GPT-4.1 Nano
2 / 9
Gemma 3 27b
5 / 9
Find an author
GPT-4.1 Nano
0 / 1
Gemma 3 27b
0 / 1
Localization
GPT-4.1 Nano
0 / 1
Gemma 3 27b
1 / 1
OCR
GPT-4.1 Nano
6 / 9
Gemma 3 27b
6 / 9
Object Counting
GPT-4.1 Nano
2 / 10
Gemma 3 27b
2 / 10
Object Detection
GPT-4.1 Nano
1 / 2
Gemma 3 27b
2 / 2
Object Measurement
GPT-4.1 Nano
0 / 2
Gemma 3 27b
0 / 2
Object Understanding
GPT-4.1 Nano
7 / 10
Gemma 3 27b
9 / 10
Receipt Reading
GPT-4.1 Nano
1 / 1
Gemma 3 27b
1 / 1
Sign Understanding
GPT-4.1 Nano
1 / 2
Gemma 3 27b
2 / 2
Spatial Relations
GPT-4.1 Nano
10 / 17
Gemma 3 27b
10 / 17
Web Action Understanding
GPT-4.1 Nano
4 / 4
Gemma 3 27b
4 / 4
Contribute a Prompt
Have an idea for a prompt? Open a pull request on the project repository!