Gemini 2.5 Flash Preview vs.Llama 4 Scout 17B
Passed:
Gemini 2.5 Flash Preview 67.1% (55/82)
Llama 4 Scout 17B 64.6% (53/82)
Average request time:
Gemini 2.5 Flash Preview 28.05s
Llama 4 Scout 17B 9.35s
Passed:
Gemini 2.5 Flash Preview 67.1% (55/82)
Llama 4 Scout 17B 64.6% (53/82)
Average request time:
Gemini 2.5 Flash Preview 28.05s
Llama 4 Scout 17B 9.35s
Summary
Annotation Understanding
Gemini 2.5 Flash Preview
2 / 2
Llama 4 Scout 17B
0 / 2
CAPTCHA
Gemini 2.5 Flash Preview
2 / 2
Llama 4 Scout 17B
2 / 2
Color Identification
Gemini 2.5 Flash Preview
1 / 1
Llama 4 Scout 17B
0 / 1
Counting nodes
Gemini 2.5 Flash Preview
0 / 1
Llama 4 Scout 17B
0 / 1
Defect Detection
Gemini 2.5 Flash Preview
11 / 15
Llama 4 Scout 17B
11 / 15
Document Understanding
Gemini 2.5 Flash Preview
5 / 10
Llama 4 Scout 17B
5 / 10
Localization
Gemini 2.5 Flash Preview
0 / 1
Llama 4 Scout 17B
1 / 1
OCR
Gemini 2.5 Flash Preview
8 / 9
Llama 4 Scout 17B
9 / 9
Object Counting
Gemini 2.5 Flash Preview
3 / 10
Llama 4 Scout 17B
2 / 10
Object Detection
Gemini 2.5 Flash Preview
2 / 2
Llama 4 Scout 17B
2 / 2
Object Measurement
Gemini 2.5 Flash Preview
0 / 2
Llama 4 Scout 17B
0 / 2
Object Understanding
Gemini 2.5 Flash Preview
9 / 10
Llama 4 Scout 17B
7 / 10
Receipt Reading
Gemini 2.5 Flash Preview
1 / 1
Llama 4 Scout 17B
0 / 1
Sign Understanding
Gemini 2.5 Flash Preview
2 / 2
Llama 4 Scout 17B
2 / 2
Spatial Relations
Gemini 2.5 Flash Preview
11 / 17
Llama 4 Scout 17B
13 / 17
Web Action Understanding
Gemini 2.5 Flash Preview
4 / 4
Llama 4 Scout 17B
4 / 4
Contribute a Prompt
Have an idea for a prompt? Open a pull request on the project repository!