Llama 4 Scout 17B vs.Gemma 3 27b
Passed:
Llama 4 Scout 17B 72.8% (59/81)
Gemma 3 27b 63.0% (51/81)
Average request time:
Llama 4 Scout 17B 41.93s
Gemma 3 27b 30.87s
Passed:
Llama 4 Scout 17B 72.8% (59/81)
Gemma 3 27b 63.0% (51/81)
Average request time:
Llama 4 Scout 17B 41.93s
Gemma 3 27b 30.87s
Summary
Annotation Understanding
Llama 4 Scout 17B
0 / 2
Gemma 3 27b
0 / 2
CAPTCHA
Llama 4 Scout 17B
2 / 2
Gemma 3 27b
2 / 2
Color Identification
Llama 4 Scout 17B
0 / 1
Gemma 3 27b
0 / 1
Counting nodes
Llama 4 Scout 17B
0 / 0
Gemma 3 27b
0 / 0
Defect Detection
Llama 4 Scout 17B
11 / 15
Gemma 3 27b
9 / 15
Document Understanding
Llama 4 Scout 17B
9 / 10
Gemma 3 27b
8 / 10
Localization
Llama 4 Scout 17B
1 / 1
Gemma 3 27b
1 / 1
OCR
Llama 4 Scout 17B
9 / 9
Gemma 3 27b
6 / 9
Object Counting
Llama 4 Scout 17B
2 / 9
Gemma 3 27b
1 / 9
Object Detection
Llama 4 Scout 17B
2 / 2
Gemma 3 27b
2 / 2
Object Measurement
Llama 4 Scout 17B
0 / 2
Gemma 3 27b
0 / 2
Object Understanding
Llama 4 Scout 17B
9 / 11
Gemma 3 27b
8 / 11
Receipt Reading
Llama 4 Scout 17B
0 / 1
Gemma 3 27b
1 / 1
Sign Understanding
Llama 4 Scout 17B
2 / 2
Gemma 3 27b
2 / 2
Spatial Relations
Llama 4 Scout 17B
12 / 17
Gemma 3 27b
11 / 17
Web Action Understanding
Llama 4 Scout 17B
4 / 4
Gemma 3 27b
4 / 4
Contribute a Prompt
Have an idea for a prompt? Open a pull request on the project repository!