Llama 4 Scout 17B vs.Gemini 1.5 Flash
Passed:
Llama 4 Scout 17B 72.8% (59/81)
Gemini 1.5 Flash 65.1% (54/83)
Average request time:
Llama 4 Scout 17B 41.93s
Gemini 1.5 Flash 13.41s
Passed:
Llama 4 Scout 17B 72.8% (59/81)
Gemini 1.5 Flash 65.1% (54/83)
Average request time:
Llama 4 Scout 17B 41.93s
Gemini 1.5 Flash 13.41s
Summary
Annotation Understanding
Llama 4 Scout 17B
0 / 2
Gemini 1.5 Flash
1 / 2
CAPTCHA
Llama 4 Scout 17B
2 / 2
Gemini 1.5 Flash
0 / 2
Color Identification
Llama 4 Scout 17B
0 / 1
Gemini 1.5 Flash
1 / 1
Counting nodes
Llama 4 Scout 17B
0 / 0
Gemini 1.5 Flash
0 / 1
Defect Detection
Llama 4 Scout 17B
11 / 15
Gemini 1.5 Flash
13 / 15
Document Understanding
Llama 4 Scout 17B
9 / 10
Gemini 1.5 Flash
8 / 10
Localization
Llama 4 Scout 17B
1 / 1
Gemini 1.5 Flash
0 / 1
OCR
Llama 4 Scout 17B
9 / 9
Gemini 1.5 Flash
8 / 9
Object Counting
Llama 4 Scout 17B
2 / 9
Gemini 1.5 Flash
0 / 10
Object Detection
Llama 4 Scout 17B
2 / 2
Gemini 1.5 Flash
1 / 2
Object Measurement
Llama 4 Scout 17B
0 / 2
Gemini 1.5 Flash
0 / 2
Object Understanding
Llama 4 Scout 17B
9 / 11
Gemini 1.5 Flash
7 / 11
Receipt Reading
Llama 4 Scout 17B
0 / 1
Gemini 1.5 Flash
1 / 1
Sign Understanding
Llama 4 Scout 17B
2 / 2
Gemini 1.5 Flash
2 / 2
Spatial Relations
Llama 4 Scout 17B
12 / 17
Gemini 1.5 Flash
12 / 17
Web Action Understanding
Llama 4 Scout 17B
4 / 4
Gemini 1.5 Flash
4 / 4
Contribute a Prompt
Have an idea for a prompt? Open a pull request on the project repository!