Gemini 2.0 Flash vs.Qwen 3.5 27B
Passed:
Gemini 2.0 Flash 65.9% (54/82)
Qwen 3.5 27B 74.4% (61/82)
Average request time:
Gemini 2.0 Flash 6.06s
Qwen 3.5 27B 1.89s
Passed:
Gemini 2.0 Flash 65.9% (54/82)
Qwen 3.5 27B 74.4% (61/82)
Average request time:
Gemini 2.0 Flash 6.06s
Qwen 3.5 27B 1.89s
Summary
Annotation Understanding
Gemini 2.0 Flash
1 / 2
Qwen 3.5 27B
1 / 2
CAPTCHA
Gemini 2.0 Flash
2 / 2
Qwen 3.5 27B
2 / 2
Color Identification
Gemini 2.0 Flash
0 / 1
Qwen 3.5 27B
1 / 1
Defect Detection
Gemini 2.0 Flash
11 / 15
Qwen 3.5 27B
12 / 15
Document Understanding
Gemini 2.0 Flash
9 / 10
Qwen 3.5 27B
7 / 10
Localization
Gemini 2.0 Flash
1 / 1
Qwen 3.5 27B
1 / 1
OCR
Gemini 2.0 Flash
9 / 9
Qwen 3.5 27B
8 / 9
Object Counting
Gemini 2.0 Flash
1 / 11
Qwen 3.5 27B
5 / 11
Object Detection
Gemini 2.0 Flash
0 / 2
Qwen 3.5 27B
1 / 2
Object Measurement
Gemini 2.0 Flash
0 / 1
Qwen 3.5 27B
1 / 1
Object Understanding
Gemini 2.0 Flash
7 / 11
Qwen 3.5 27B
9 / 11
Receipt Reading
Gemini 2.0 Flash
1 / 1
Qwen 3.5 27B
1 / 1
Sign Understanding
Gemini 2.0 Flash
2 / 2
Qwen 3.5 27B
2 / 2
Spatial Relations
Gemini 2.0 Flash
10 / 17
Qwen 3.5 27B
13 / 17
Web Action Understanding
Gemini 2.0 Flash
4 / 4
Qwen 3.5 27B
4 / 4
Contribute a Prompt
Have an idea for a prompt? Open a pull request on the project repository!