Mistral Small 3.1 24B vs.Kimi k2.5
Passed:
Mistral Small 3.1 24B 44.6% (37/83)
Kimi k2.5 73.5% (50/68)
Average request time:
Mistral Small 3.1 24B 15.16s
Kimi k2.5 44.70s
Passed:
Mistral Small 3.1 24B 44.6% (37/83)
Kimi k2.5 73.5% (50/68)
Average request time:
Mistral Small 3.1 24B 15.16s
Kimi k2.5 44.70s
Summary
Annotation Understanding
Mistral Small 3.1 24B
0 / 2
Kimi k2.5
1 / 1
CAPTCHA
Mistral Small 3.1 24B
2 / 2
Kimi k2.5
2 / 2
Color Identification
Mistral Small 3.1 24B
1 / 1
Kimi k2.5
1 / 1
Defect Detection
Mistral Small 3.1 24B
8 / 15
Kimi k2.5
8 / 14
Document Understanding
Mistral Small 3.1 24B
5 / 10
Kimi k2.5
8 / 8
Localization
Mistral Small 3.1 24B
0 / 1
Kimi k2.5
1 / 1
OCR
Mistral Small 3.1 24B
7 / 9
Kimi k2.5
7 / 9
Object Counting
Mistral Small 3.1 24B
0 / 11
Kimi k2.5
1 / 3
Object Detection
Mistral Small 3.1 24B
1 / 2
Kimi k2.5
1 / 2
Object Measurement
Mistral Small 3.1 24B
0 / 1
Kimi k2.5
0 / 1
Object Understanding
Mistral Small 3.1 24B
4 / 11
Kimi k2.5
9 / 11
Receipt Reading
Mistral Small 3.1 24B
1 / 1
Kimi k2.5
1 / 1
Sign Understanding
Mistral Small 3.1 24B
0 / 2
Kimi k2.5
2 / 2
Spatial Relations
Mistral Small 3.1 24B
6 / 17
Kimi k2.5
12 / 15
Web Action Understanding
Mistral Small 3.1 24B
4 / 4
Kimi k2.5
3 / 4
Contribute a Prompt
Have an idea for a prompt? Open a pull request on the project repository!