Qwen 2.5 VL 7B vs.Gemma 3 27b
Passed:
Qwen 2.5 VL 7B 56.1% (46/82)
Gemma 3 27b 64.6% (53/82)
Average request time:
Qwen 2.5 VL 7B 10.18s
Gemma 3 27b 11.02s
Passed:
Qwen 2.5 VL 7B 56.1% (46/82)
Gemma 3 27b 64.6% (53/82)
Average request time:
Qwen 2.5 VL 7B 10.18s
Gemma 3 27b 11.02s
Summary
Annotation Understanding
Qwen 2.5 VL 7B
2 / 2
Gemma 3 27b
0 / 2
CAPTCHA
Qwen 2.5 VL 7B
2 / 2
Gemma 3 27b
2 / 2
Color Identification
Qwen 2.5 VL 7B
1 / 1
Gemma 3 27b
1 / 1
Counting nodes
Qwen 2.5 VL 7B
0 / 1
Gemma 3 27b
0 / 1
Defect Detection
Qwen 2.5 VL 7B
10 / 15
Gemma 3 27b
12 / 15
Document Understanding
Qwen 2.5 VL 7B
5 / 10
Gemma 3 27b
5 / 10
Localization
Qwen 2.5 VL 7B
0 / 1
Gemma 3 27b
1 / 1
OCR
Qwen 2.5 VL 7B
7 / 9
Gemma 3 27b
6 / 9
Object Counting
Qwen 2.5 VL 7B
1 / 10
Gemma 3 27b
2 / 10
Object Detection
Qwen 2.5 VL 7B
1 / 2
Gemma 3 27b
2 / 2
Object Measurement
Qwen 2.5 VL 7B
0 / 2
Gemma 3 27b
0 / 2
Object Understanding
Qwen 2.5 VL 7B
7 / 10
Gemma 3 27b
9 / 10
Receipt Reading
Qwen 2.5 VL 7B
1 / 1
Gemma 3 27b
1 / 1
Sign Understanding
Qwen 2.5 VL 7B
2 / 2
Gemma 3 27b
2 / 2
Spatial Relations
Qwen 2.5 VL 7B
10 / 17
Gemma 3 27b
10 / 17
Web Action Understanding
Qwen 2.5 VL 7B
3 / 4
Gemma 3 27b
4 / 4
Contribute a Prompt
Have an idea for a prompt? Open a pull request on the project repository!