adjustable glasses illustration eye chart illustration clipboard illustration lenses illustration

Qwen 2.5 VL 7B vs.Gemma 3 4B

Passed:
Qwen 2.5 VL 7B 55.6% (45/81)
Gemma 3 4B 42.2% (35/83)
Average request time:
Qwen 2.5 VL 7B 45.63s
Gemma 3 4B 15.86s

Summary

Annotation Understanding
Qwen 2.5 VL 7B 1 / 2
Gemma 3 4B 0 / 2
CAPTCHA
Qwen 2.5 VL 7B 2 / 2
Gemma 3 4B 2 / 2
Color Identification
Qwen 2.5 VL 7B 0 / 1
Gemma 3 4B 0 / 1
Counting nodes
Qwen 2.5 VL 7B 0 / 0
Gemma 3 4B 0 / 1
Defect Detection
Qwen 2.5 VL 7B 9 / 15
Gemma 3 4B 9 / 15
Document Understanding
Qwen 2.5 VL 7B 8 / 10
Gemma 3 4B 6 / 10
Localization
Qwen 2.5 VL 7B 1 / 1
Gemma 3 4B 0 / 1
OCR
Qwen 2.5 VL 7B 6 / 9
Gemma 3 4B 6 / 9
Object Counting
Qwen 2.5 VL 7B 1 / 9
Gemma 3 4B 0 / 10
Object Detection
Qwen 2.5 VL 7B 1 / 2
Gemma 3 4B 2 / 2
Object Measurement
Qwen 2.5 VL 7B 0 / 2
Gemma 3 4B 0 / 2
Object Understanding
Qwen 2.5 VL 7B 5 / 11
Gemma 3 4B 5 / 11
Receipt Reading
Qwen 2.5 VL 7B 0 / 1
Gemma 3 4B 0 / 1
Sign Understanding
Qwen 2.5 VL 7B 2 / 2
Gemma 3 4B 2 / 2
Spatial Relations
Qwen 2.5 VL 7B 11 / 17
Gemma 3 4B 4 / 17
Web Action Understanding
Qwen 2.5 VL 7B 4 / 4
Gemma 3 4B 2 / 4

Contribute a Prompt