Gemini 2.0 Flash vs.Llama 3 11B Vision
Passed:
Gemini 2.0 Flash 67.1% (55/82)
Llama 3 11B Vision 52.4% (43/82)
Average request time:
Gemini 2.0 Flash 9.11s
Llama 3 11B Vision 20.50s
Passed:
Gemini 2.0 Flash 67.1% (55/82)
Llama 3 11B Vision 52.4% (43/82)
Average request time:
Gemini 2.0 Flash 9.11s
Llama 3 11B Vision 20.50s
Summary
Annotation Understanding
Gemini 2.0 Flash
2 / 2
Llama 3 11B Vision
1 / 2
CAPTCHA
Gemini 2.0 Flash
2 / 2
Llama 3 11B Vision
0 / 2
Color Identification
Gemini 2.0 Flash
1 / 1
Llama 3 11B Vision
0 / 1
Counting nodes
Gemini 2.0 Flash
0 / 1
Llama 3 11B Vision
0 / 1
Defect Detection
Gemini 2.0 Flash
10 / 15
Llama 3 11B Vision
5 / 15
Document Understanding
Gemini 2.0 Flash
6 / 10
Llama 3 11B Vision
4 / 10
Localization
Gemini 2.0 Flash
1 / 1
Llama 3 11B Vision
0 / 1
OCR
Gemini 2.0 Flash
7 / 9
Llama 3 11B Vision
7 / 9
Object Counting
Gemini 2.0 Flash
3 / 10
Llama 3 11B Vision
4 / 10
Object Detection
Gemini 2.0 Flash
1 / 2
Llama 3 11B Vision
1 / 2
Object Measurement
Gemini 2.0 Flash
0 / 2
Llama 3 11B Vision
0 / 2
Object Understanding
Gemini 2.0 Flash
8 / 10
Llama 3 11B Vision
5 / 10
Receipt Reading
Gemini 2.0 Flash
1 / 1
Llama 3 11B Vision
1 / 1
Sign Understanding
Gemini 2.0 Flash
2 / 2
Llama 3 11B Vision
0 / 2
Spatial Relations
Gemini 2.0 Flash
13 / 17
Llama 3 11B Vision
14 / 17
Web Action Understanding
Gemini 2.0 Flash
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!