Gemini 3.1 Pro vs.Qwen 3.5 122B (A10B)
Passed:
Gemini 3.1 Pro 81.7% (67/82)
Qwen 3.5 122B (A10B) 78.0% (64/82)
Average request time:
Gemini 3.1 Pro 12.43s
Qwen 3.5 122B (A10B) 1.54s
Passed:
Gemini 3.1 Pro 81.7% (67/82)
Qwen 3.5 122B (A10B) 78.0% (64/82)
Average request time:
Gemini 3.1 Pro 12.43s
Qwen 3.5 122B (A10B) 1.54s
Summary
Annotation Understanding
Gemini 3.1 Pro
2 / 2
Qwen 3.5 122B (A10B)
1 / 2
CAPTCHA
Gemini 3.1 Pro
2 / 2
Qwen 3.5 122B (A10B)
2 / 2
Color Identification
Gemini 3.1 Pro
1 / 1
Qwen 3.5 122B (A10B)
1 / 1
Defect Detection
Gemini 3.1 Pro
11 / 15
Qwen 3.5 122B (A10B)
13 / 15
Document Understanding
Gemini 3.1 Pro
8 / 10
Qwen 3.5 122B (A10B)
9 / 10
Localization
Gemini 3.1 Pro
1 / 1
Qwen 3.5 122B (A10B)
1 / 1
OCR
Gemini 3.1 Pro
9 / 9
Qwen 3.5 122B (A10B)
7 / 9
Object Counting
Gemini 3.1 Pro
5 / 11
Qwen 3.5 122B (A10B)
5 / 11
Object Detection
Gemini 3.1 Pro
2 / 2
Qwen 3.5 122B (A10B)
2 / 2
Object Measurement
Gemini 3.1 Pro
1 / 1
Qwen 3.5 122B (A10B)
1 / 1
Object Understanding
Gemini 3.1 Pro
11 / 11
Qwen 3.5 122B (A10B)
8 / 11
Receipt Reading
Gemini 3.1 Pro
1 / 1
Qwen 3.5 122B (A10B)
1 / 1
Sign Understanding
Gemini 3.1 Pro
2 / 2
Qwen 3.5 122B (A10B)
2 / 2
Spatial Relations
Gemini 3.1 Pro
12 / 17
Qwen 3.5 122B (A10B)
14 / 17
Web Action Understanding
Gemini 3.1 Pro
4 / 4
Qwen 3.5 122B (A10B)
4 / 4
Contribute a Prompt
Have an idea for a prompt? Open a pull request on the project repository!