Qwen 2.5 VL 7B vs.Llama 4 Scout 17B
Passed:
Qwen 2.5 VL 7B 55.6% (45/81)
Llama 4 Scout 17B 72.8% (59/81)
Average request time:
Qwen 2.5 VL 7B 45.63s
Llama 4 Scout 17B 41.93s
Passed:
Qwen 2.5 VL 7B 55.6% (45/81)
Llama 4 Scout 17B 72.8% (59/81)
Average request time:
Qwen 2.5 VL 7B 45.63s
Llama 4 Scout 17B 41.93s
Summary
Annotation Understanding
Qwen 2.5 VL 7B
1 / 2
Llama 4 Scout 17B
0 / 2
CAPTCHA
Qwen 2.5 VL 7B
2 / 2
Llama 4 Scout 17B
2 / 2
Color Identification
Qwen 2.5 VL 7B
0 / 1
Llama 4 Scout 17B
0 / 1
Counting nodes
Qwen 2.5 VL 7B
0 / 0
Llama 4 Scout 17B
0 / 0
Defect Detection
Qwen 2.5 VL 7B
9 / 15
Llama 4 Scout 17B
11 / 15
Document Understanding
Qwen 2.5 VL 7B
8 / 10
Llama 4 Scout 17B
9 / 10
Localization
Qwen 2.5 VL 7B
1 / 1
Llama 4 Scout 17B
1 / 1
OCR
Qwen 2.5 VL 7B
6 / 9
Llama 4 Scout 17B
9 / 9
Object Counting
Qwen 2.5 VL 7B
1 / 9
Llama 4 Scout 17B
2 / 9
Object Detection
Qwen 2.5 VL 7B
1 / 2
Llama 4 Scout 17B
2 / 2
Object Measurement
Qwen 2.5 VL 7B
0 / 2
Llama 4 Scout 17B
0 / 2
Object Understanding
Qwen 2.5 VL 7B
5 / 11
Llama 4 Scout 17B
9 / 11
Receipt Reading
Qwen 2.5 VL 7B
0 / 1
Llama 4 Scout 17B
0 / 1
Sign Understanding
Qwen 2.5 VL 7B
2 / 2
Llama 4 Scout 17B
2 / 2
Spatial Relations
Qwen 2.5 VL 7B
11 / 17
Llama 4 Scout 17B
12 / 17
Web Action Understanding
Qwen 2.5 VL 7B
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!