adjustable glasses illustration eye chart illustration clipboard illustration lenses illustration

Claude 3.5 Haiku vs.Kimi k2.5

Passed:
Claude 3.5 Haiku 65.1% (54/83)
Kimi k2.5 73.5% (50/68)
Average request time:
Claude 3.5 Haiku 16.75s
Kimi k2.5 44.70s

Summary

Annotation Understanding
Claude 3.5 Haiku 2 / 2
Kimi k2.5 1 / 1
CAPTCHA
Claude 3.5 Haiku 0 / 2
Kimi k2.5 2 / 2
Color Identification
Claude 3.5 Haiku 0 / 1
Kimi k2.5 1 / 1
Defect Detection
Claude 3.5 Haiku 10 / 15
Kimi k2.5 8 / 14
Document Understanding
Claude 3.5 Haiku 8 / 10
Kimi k2.5 8 / 8
Localization
Claude 3.5 Haiku 0 / 1
Kimi k2.5 1 / 1
OCR
Claude 3.5 Haiku 7 / 9
Kimi k2.5 7 / 9
Object Counting
Claude 3.5 Haiku 5 / 11
Kimi k2.5 1 / 3
Object Detection
Claude 3.5 Haiku 2 / 2
Kimi k2.5 1 / 2
Object Measurement
Claude 3.5 Haiku 0 / 1
Kimi k2.5 0 / 1
Object Understanding
Claude 3.5 Haiku 7 / 11
Kimi k2.5 9 / 11
Receipt Reading
Claude 3.5 Haiku 1 / 1
Kimi k2.5 1 / 1
Sign Understanding
Claude 3.5 Haiku 2 / 2
Kimi k2.5 2 / 2
Spatial Relations
Claude 3.5 Haiku 8 / 17
Kimi k2.5 12 / 15
Web Action Understanding
Claude 3.5 Haiku 4 / 4
Kimi k2.5 3 / 4

Contribute a Prompt