Gemma 3 27b vs.Kimi k2.5
Passed:
Gemma 3 27b 63.0% (51/81)
Kimi k2.5 73.5% (50/68)
Average request time:
Gemma 3 27b 30.87s
Kimi k2.5 44.70s
Passed:
Gemma 3 27b 63.0% (51/81)
Kimi k2.5 73.5% (50/68)
Average request time:
Gemma 3 27b 30.87s
Kimi k2.5 44.70s
Summary
Annotation Understanding
Gemma 3 27b
0 / 2
Kimi k2.5
1 / 1
CAPTCHA
Gemma 3 27b
2 / 2
Kimi k2.5
2 / 2
Color Identification
Gemma 3 27b
0 / 1
Kimi k2.5
1 / 1
Defect Detection
Gemma 3 27b
9 / 15
Kimi k2.5
8 / 14
Document Understanding
Gemma 3 27b
8 / 10
Kimi k2.5
8 / 8
Localization
Gemma 3 27b
1 / 1
Kimi k2.5
1 / 1
OCR
Gemma 3 27b
6 / 9
Kimi k2.5
7 / 9
Object Counting
Gemma 3 27b
1 / 9
Kimi k2.5
1 / 3
Object Detection
Gemma 3 27b
2 / 2
Kimi k2.5
1 / 2
Object Measurement
Gemma 3 27b
0 / 1
Kimi k2.5
0 / 1
Object Understanding
Gemma 3 27b
8 / 11
Kimi k2.5
9 / 11
Receipt Reading
Gemma 3 27b
1 / 1
Kimi k2.5
1 / 1
Sign Understanding
Gemma 3 27b
2 / 2
Kimi k2.5
2 / 2
Spatial Relations
Gemma 3 27b
11 / 17
Kimi k2.5
12 / 15
Web Action Understanding
Gemma 3 27b
4 / 4
Kimi k2.5
3 / 4
Contribute a Prompt
Have an idea for a prompt? Open a pull request on the project repository!