Gemini 3.1 Pro (Tools) vs.Qwen 2.5 VL 7B
Passed:
Gemini 3.1 Pro (Tools) 84.1% (69/82)
Qwen 2.5 VL 7B 55.6% (45/81)
Average request time:
Gemini 3.1 Pro (Tools) 26.26s
Qwen 2.5 VL 7B 45.63s
Passed:
Gemini 3.1 Pro (Tools) 84.1% (69/82)
Qwen 2.5 VL 7B 55.6% (45/81)
Average request time:
Gemini 3.1 Pro (Tools) 26.26s
Qwen 2.5 VL 7B 45.63s
Summary
Annotation Understanding
Gemini 3.1 Pro (Tools)
1 / 2
Qwen 2.5 VL 7B
1 / 2
CAPTCHA
Gemini 3.1 Pro (Tools)
2 / 2
Qwen 2.5 VL 7B
2 / 2
Color Identification
Gemini 3.1 Pro (Tools)
1 / 1
Qwen 2.5 VL 7B
0 / 1
Defect Detection
Gemini 3.1 Pro (Tools)
12 / 15
Qwen 2.5 VL 7B
9 / 15
Document Understanding
Gemini 3.1 Pro (Tools)
9 / 10
Qwen 2.5 VL 7B
8 / 10
Localization
Gemini 3.1 Pro (Tools)
1 / 1
Qwen 2.5 VL 7B
1 / 1
OCR
Gemini 3.1 Pro (Tools)
9 / 9
Qwen 2.5 VL 7B
6 / 9
Object Counting
Gemini 3.1 Pro (Tools)
5 / 11
Qwen 2.5 VL 7B
1 / 9
Object Detection
Gemini 3.1 Pro (Tools)
2 / 2
Qwen 2.5 VL 7B
1 / 2
Object Measurement
Gemini 3.1 Pro (Tools)
1 / 1
Qwen 2.5 VL 7B
0 / 1
Object Understanding
Gemini 3.1 Pro (Tools)
10 / 11
Qwen 2.5 VL 7B
5 / 11
Receipt Reading
Gemini 3.1 Pro (Tools)
1 / 1
Qwen 2.5 VL 7B
0 / 1
Sign Understanding
Gemini 3.1 Pro (Tools)
2 / 2
Qwen 2.5 VL 7B
2 / 2
Spatial Relations
Gemini 3.1 Pro (Tools)
14 / 17
Qwen 2.5 VL 7B
11 / 17
Web Action Understanding
Gemini 3.1 Pro (Tools)
4 / 4
Qwen 2.5 VL 7B
4 / 4
Contribute a Prompt
Have an idea for a prompt? Open a pull request on the project repository!