Qwen 3.5 4B vs.Molmo2 8B
Passed:
Qwen 3.5 4B 63.4% (52/82)
Molmo2 8B 53.7% (44/82)
Average request time:
Qwen 3.5 4B 5.81s
Molmo2 8B 1.16s
Passed:
Qwen 3.5 4B 63.4% (52/82)
Molmo2 8B 53.7% (44/82)
Average request time:
Qwen 3.5 4B 5.81s
Molmo2 8B 1.16s
Summary
Annotation Understanding
Qwen 3.5 4B
0 / 2
Molmo2 8B
0 / 2
CAPTCHA
Qwen 3.5 4B
2 / 2
Molmo2 8B
0 / 2
Color Identification
Qwen 3.5 4B
0 / 1
Molmo2 8B
1 / 1
Defect Detection
Qwen 3.5 4B
12 / 15
Molmo2 8B
10 / 15
Document Understanding
Qwen 3.5 4B
7 / 10
Molmo2 8B
6 / 10
Localization
Qwen 3.5 4B
0 / 1
Molmo2 8B
1 / 1
OCR
Qwen 3.5 4B
7 / 9
Molmo2 8B
6 / 9
Object Counting
Qwen 3.5 4B
4 / 11
Molmo2 8B
1 / 11
Object Detection
Qwen 3.5 4B
2 / 2
Molmo2 8B
1 / 2
Object Measurement
Qwen 3.5 4B
0 / 1
Molmo2 8B
0 / 1
Object Understanding
Qwen 3.5 4B
7 / 11
Molmo2 8B
7 / 11
Receipt Reading
Qwen 3.5 4B
1 / 1
Molmo2 8B
0 / 1
Sign Understanding
Qwen 3.5 4B
2 / 2
Molmo2 8B
2 / 2
Spatial Relations
Qwen 3.5 4B
8 / 17
Molmo2 8B
9 / 17
Web Action Understanding
Qwen 3.5 4B
4 / 4
Molmo2 8B
4 / 4
Contribute a Prompt
Have an idea for a prompt? Open a pull request on the project repository!