adjustable glasses illustration eye chart illustration clipboard illustration lenses illustration

Claude 3.5 Haiku vs.Qwen 3.5 122B (A10B)

Passed:
Claude 3.5 Haiku 65.1% (54/83)
Qwen 3.5 122B (A10B) 78.0% (64/82)
Average request time:
Claude 3.5 Haiku 16.75s
Qwen 3.5 122B (A10B) 1.54s

Summary

Annotation Understanding
Claude 3.5 Haiku 2 / 2
Qwen 3.5 122B (A10B) 1 / 2
CAPTCHA
Claude 3.5 Haiku 0 / 2
Qwen 3.5 122B (A10B) 2 / 2
Color Identification
Claude 3.5 Haiku 0 / 1
Qwen 3.5 122B (A10B) 1 / 1
Defect Detection
Claude 3.5 Haiku 10 / 15
Qwen 3.5 122B (A10B) 13 / 15
Document Understanding
Claude 3.5 Haiku 8 / 10
Qwen 3.5 122B (A10B) 9 / 10
Localization
Claude 3.5 Haiku 0 / 1
Qwen 3.5 122B (A10B) 1 / 1
OCR
Claude 3.5 Haiku 7 / 9
Qwen 3.5 122B (A10B) 7 / 9
Object Counting
Claude 3.5 Haiku 5 / 11
Qwen 3.5 122B (A10B) 5 / 11
Object Detection
Claude 3.5 Haiku 2 / 2
Qwen 3.5 122B (A10B) 2 / 2
Object Measurement
Claude 3.5 Haiku 0 / 1
Qwen 3.5 122B (A10B) 1 / 1
Object Understanding
Claude 3.5 Haiku 7 / 11
Qwen 3.5 122B (A10B) 8 / 11
Receipt Reading
Claude 3.5 Haiku 1 / 1
Qwen 3.5 122B (A10B) 1 / 1
Sign Understanding
Claude 3.5 Haiku 2 / 2
Qwen 3.5 122B (A10B) 2 / 2
Spatial Relations
Claude 3.5 Haiku 8 / 17
Qwen 3.5 122B (A10B) 14 / 17
Web Action Understanding
Claude 3.5 Haiku 4 / 4
Qwen 3.5 122B (A10B) 4 / 4

Contribute a Prompt