GPT-4.1 vs.Llama 3 11B Vision
Passed:
GPT-4.1 73.2% (60/82)
Llama 3 11B Vision 52.4% (43/82)
Average request time:
GPT-4.1 14.91s
Llama 3 11B Vision 20.50s
Passed:
GPT-4.1 73.2% (60/82)
Llama 3 11B Vision 52.4% (43/82)
Average request time:
GPT-4.1 14.91s
Llama 3 11B Vision 20.50s
Summary
Annotation Understanding
GPT-4.1
1 / 2
Llama 3 11B Vision
1 / 2
CAPTCHA
GPT-4.1
0 / 2
Llama 3 11B Vision
0 / 2
Color Identification
GPT-4.1
1 / 1
Llama 3 11B Vision
0 / 1
Counting nodes
GPT-4.1
0 / 1
Llama 3 11B Vision
0 / 1
Defect Detection
GPT-4.1
13 / 15
Llama 3 11B Vision
5 / 15
Document Understanding
GPT-4.1
5 / 10
Llama 3 11B Vision
4 / 10
Localization
GPT-4.1
1 / 1
Llama 3 11B Vision
0 / 1
OCR
GPT-4.1
9 / 9
Llama 3 11B Vision
7 / 9
Object Counting
GPT-4.1
2 / 10
Llama 3 11B Vision
4 / 10
Object Detection
GPT-4.1
2 / 2
Llama 3 11B Vision
1 / 2
Object Measurement
GPT-4.1
1 / 2
Llama 3 11B Vision
0 / 2
Object Understanding
GPT-4.1
9 / 10
Llama 3 11B Vision
5 / 10
Receipt Reading
GPT-4.1
1 / 1
Llama 3 11B Vision
1 / 1
Sign Understanding
GPT-4.1
2 / 2
Llama 3 11B Vision
0 / 2
Spatial Relations
GPT-4.1
14 / 17
Llama 3 11B Vision
14 / 17
Web Action Understanding
GPT-4.1
4 / 4
Llama 3 11B Vision
4 / 4
Contribute a Prompt
Have an idea for a prompt? Open a pull request on the project repository!