adjustable glasses illustration eye chart illustration clipboard illustration lenses illustration

Claude 3.7 Sonnet vs.Gemma 4 31B

Passed:
Claude 3.7 Sonnet 63.9% (53/83)
Gemma 4 31B 72.2% (39/54)
Average request time:
Claude 3.7 Sonnet 13.98s
Gemma 4 31B 15.30s

Summary

Annotation Understanding
Claude 3.7 Sonnet 0 / 2
Gemma 4 31B 0 / 1
CAPTCHA
Claude 3.7 Sonnet 2 / 2
Gemma 4 31B 2 / 2
Color Identification
Claude 3.7 Sonnet 1 / 1
Gemma 4 31B 0 / 0
Defect Detection
Claude 3.7 Sonnet 10 / 15
Gemma 4 31B 6 / 8
Document Understanding
Claude 3.7 Sonnet 9 / 10
Gemma 4 31B 7 / 7
Localization
Claude 3.7 Sonnet 1 / 1
Gemma 4 31B 0 / 1
OCR
Claude 3.7 Sonnet 7 / 9
Gemma 4 31B 4 / 4
Object Counting
Claude 3.7 Sonnet 2 / 11
Gemma 4 31B 2 / 8
Object Detection
Claude 3.7 Sonnet 2 / 2
Gemma 4 31B 1 / 2
Object Measurement
Claude 3.7 Sonnet 0 / 1
Gemma 4 31B 0 / 0
Object Understanding
Claude 3.7 Sonnet 7 / 11
Gemma 4 31B 4 / 7
Receipt Reading
Claude 3.7 Sonnet 1 / 1
Gemma 4 31B 1 / 1
Sign Understanding
Claude 3.7 Sonnet 2 / 2
Gemma 4 31B 1 / 1
Spatial Relations
Claude 3.7 Sonnet 9 / 17
Gemma 4 31B 10 / 13
Web Action Understanding
Claude 3.7 Sonnet 4 / 4
Gemma 4 31B 4 / 4

Contribute a Prompt