Molmo2 8B vs.Qwen 3.5 2B
Passed:
Molmo2 8B 53.7% (44/82)
Qwen 3.5 2B 47.6% (39/82)
Average request time:
Molmo2 8B 1.16s
Qwen 3.5 2B 6.33s
Passed:
Molmo2 8B 53.7% (44/82)
Qwen 3.5 2B 47.6% (39/82)
Average request time:
Molmo2 8B 1.16s
Qwen 3.5 2B 6.33s
Summary
Annotation Understanding
Molmo2 8B
0 / 2
Qwen 3.5 2B
0 / 2
CAPTCHA
Molmo2 8B
0 / 2
Qwen 3.5 2B
0 / 2
Color Identification
Molmo2 8B
1 / 1
Qwen 3.5 2B
0 / 1
Defect Detection
Molmo2 8B
10 / 15
Qwen 3.5 2B
6 / 15
Document Understanding
Molmo2 8B
6 / 10
Qwen 3.5 2B
7 / 10
Localization
Molmo2 8B
1 / 1
Qwen 3.5 2B
0 / 1
OCR
Molmo2 8B
6 / 9
Qwen 3.5 2B
6 / 9
Object Counting
Molmo2 8B
1 / 11
Qwen 3.5 2B
3 / 11
Object Detection
Molmo2 8B
1 / 2
Qwen 3.5 2B
1 / 2
Object Measurement
Molmo2 8B
0 / 1
Qwen 3.5 2B
0 / 1
Object Understanding
Molmo2 8B
7 / 11
Qwen 3.5 2B
3 / 11
Receipt Reading
Molmo2 8B
0 / 1
Qwen 3.5 2B
1 / 1
Sign Understanding
Molmo2 8B
2 / 2
Qwen 3.5 2B
2 / 2
Spatial Relations
Molmo2 8B
9 / 17
Qwen 3.5 2B
8 / 17
Web Action Understanding
Molmo2 8B
4 / 4
Qwen 3.5 2B
4 / 4
Contribute a Prompt
Have an idea for a prompt? Open a pull request on the project repository!