Qwen 3.5 122B (A10B) vs.Kimi k2.5
Passed:
Qwen 3.5 122B (A10B) 78.0% (64/82)
Kimi k2.5 73.5% (50/68)
Average request time:
Qwen 3.5 122B (A10B) 1.54s
Kimi k2.5 44.70s
Passed:
Qwen 3.5 122B (A10B) 78.0% (64/82)
Kimi k2.5 73.5% (50/68)
Average request time:
Qwen 3.5 122B (A10B) 1.54s
Kimi k2.5 44.70s
Summary
Annotation Understanding
Qwen 3.5 122B (A10B)
1 / 2
Kimi k2.5
1 / 1
CAPTCHA
Qwen 3.5 122B (A10B)
2 / 2
Kimi k2.5
2 / 2
Color Identification
Qwen 3.5 122B (A10B)
1 / 1
Kimi k2.5
1 / 1
Defect Detection
Qwen 3.5 122B (A10B)
13 / 15
Kimi k2.5
8 / 14
Document Understanding
Qwen 3.5 122B (A10B)
9 / 10
Kimi k2.5
8 / 8
Localization
Qwen 3.5 122B (A10B)
1 / 1
Kimi k2.5
1 / 1
OCR
Qwen 3.5 122B (A10B)
7 / 9
Kimi k2.5
7 / 9
Object Counting
Qwen 3.5 122B (A10B)
5 / 11
Kimi k2.5
1 / 3
Object Detection
Qwen 3.5 122B (A10B)
2 / 2
Kimi k2.5
1 / 2
Object Measurement
Qwen 3.5 122B (A10B)
1 / 1
Kimi k2.5
0 / 1
Object Understanding
Qwen 3.5 122B (A10B)
8 / 11
Kimi k2.5
9 / 11
Receipt Reading
Qwen 3.5 122B (A10B)
1 / 1
Kimi k2.5
1 / 1
Sign Understanding
Qwen 3.5 122B (A10B)
2 / 2
Kimi k2.5
2 / 2
Spatial Relations
Qwen 3.5 122B (A10B)
14 / 17
Kimi k2.5
12 / 15
Web Action Understanding
Qwen 3.5 122B (A10B)
4 / 4
Kimi k2.5
3 / 4
Contribute a Prompt
Have an idea for a prompt? Open a pull request on the project repository!