Gemini 3.1 Pro vs.Kimi k2.5
Passed:
Gemini 3.1 Pro 81.7% (67/82)
Kimi k2.5 73.5% (50/68)
Average request time:
Gemini 3.1 Pro 12.43s
Kimi k2.5 44.70s
Passed:
Gemini 3.1 Pro 81.7% (67/82)
Kimi k2.5 73.5% (50/68)
Average request time:
Gemini 3.1 Pro 12.43s
Kimi k2.5 44.70s
Summary
Annotation Understanding
Gemini 3.1 Pro
2 / 2
Kimi k2.5
1 / 1
CAPTCHA
Gemini 3.1 Pro
2 / 2
Kimi k2.5
2 / 2
Color Identification
Gemini 3.1 Pro
1 / 1
Kimi k2.5
1 / 1
Defect Detection
Gemini 3.1 Pro
11 / 15
Kimi k2.5
8 / 14
Document Understanding
Gemini 3.1 Pro
8 / 10
Kimi k2.5
8 / 8
Localization
Gemini 3.1 Pro
1 / 1
Kimi k2.5
1 / 1
OCR
Gemini 3.1 Pro
9 / 9
Kimi k2.5
7 / 9
Object Counting
Gemini 3.1 Pro
5 / 11
Kimi k2.5
1 / 3
Object Detection
Gemini 3.1 Pro
2 / 2
Kimi k2.5
1 / 2
Object Measurement
Gemini 3.1 Pro
1 / 1
Kimi k2.5
0 / 1
Object Understanding
Gemini 3.1 Pro
11 / 11
Kimi k2.5
9 / 11
Receipt Reading
Gemini 3.1 Pro
1 / 1
Kimi k2.5
1 / 1
Sign Understanding
Gemini 3.1 Pro
2 / 2
Kimi k2.5
2 / 2
Spatial Relations
Gemini 3.1 Pro
12 / 17
Kimi k2.5
12 / 15
Web Action Understanding
Gemini 3.1 Pro
4 / 4
Kimi k2.5
3 / 4
Contribute a Prompt
Have an idea for a prompt? Open a pull request on the project repository!