Qwen 3.5 4B vs.Kimi k2.5
Passed:
Qwen 3.5 4B 63.4% (52/82)
Kimi k2.5 73.5% (50/68)
Average request time:
Qwen 3.5 4B 5.81s
Kimi k2.5 44.70s
Passed:
Qwen 3.5 4B 63.4% (52/82)
Kimi k2.5 73.5% (50/68)
Average request time:
Qwen 3.5 4B 5.81s
Kimi k2.5 44.70s
Summary
Annotation Understanding
Qwen 3.5 4B
0 / 2
Kimi k2.5
1 / 1
CAPTCHA
Qwen 3.5 4B
2 / 2
Kimi k2.5
2 / 2
Color Identification
Qwen 3.5 4B
0 / 1
Kimi k2.5
1 / 1
Defect Detection
Qwen 3.5 4B
12 / 15
Kimi k2.5
8 / 14
Document Understanding
Qwen 3.5 4B
7 / 10
Kimi k2.5
8 / 8
Localization
Qwen 3.5 4B
0 / 1
Kimi k2.5
1 / 1
OCR
Qwen 3.5 4B
7 / 9
Kimi k2.5
7 / 9
Object Counting
Qwen 3.5 4B
4 / 11
Kimi k2.5
1 / 3
Object Detection
Qwen 3.5 4B
2 / 2
Kimi k2.5
1 / 2
Object Measurement
Qwen 3.5 4B
0 / 1
Kimi k2.5
0 / 1
Object Understanding
Qwen 3.5 4B
7 / 11
Kimi k2.5
9 / 11
Receipt Reading
Qwen 3.5 4B
1 / 1
Kimi k2.5
1 / 1
Sign Understanding
Qwen 3.5 4B
2 / 2
Kimi k2.5
2 / 2
Spatial Relations
Qwen 3.5 4B
8 / 17
Kimi k2.5
12 / 15
Web Action Understanding
Qwen 3.5 4B
4 / 4
Kimi k2.5
3 / 4
Contribute a Prompt
Have an idea for a prompt? Open a pull request on the project repository!