Claude 4 Sonnet vs.Gemma 4 31B
Passed:
Claude 4 Sonnet 71.1% (59/83)
Gemma 4 31B 72.2% (39/54)
Average request time:
Claude 4 Sonnet 19.72s
Gemma 4 31B 15.30s
Passed:
Claude 4 Sonnet 71.1% (59/83)
Gemma 4 31B 72.2% (39/54)
Average request time:
Claude 4 Sonnet 19.72s
Gemma 4 31B 15.30s
Summary
Annotation Understanding
Claude 4 Sonnet
2 / 2
Gemma 4 31B
0 / 1
CAPTCHA
Claude 4 Sonnet
2 / 2
Gemma 4 31B
2 / 2
Color Identification
Claude 4 Sonnet
0 / 1
Gemma 4 31B
0 / 0
Defect Detection
Claude 4 Sonnet
12 / 15
Gemma 4 31B
6 / 8
Document Understanding
Claude 4 Sonnet
9 / 10
Gemma 4 31B
7 / 7
Localization
Claude 4 Sonnet
0 / 1
Gemma 4 31B
0 / 1
OCR
Claude 4 Sonnet
7 / 9
Gemma 4 31B
4 / 4
Object Counting
Claude 4 Sonnet
2 / 11
Gemma 4 31B
2 / 8
Object Detection
Claude 4 Sonnet
2 / 2
Gemma 4 31B
1 / 2
Object Measurement
Claude 4 Sonnet
1 / 1
Gemma 4 31B
0 / 0
Object Understanding
Claude 4 Sonnet
8 / 11
Gemma 4 31B
4 / 7
Receipt Reading
Claude 4 Sonnet
1 / 1
Gemma 4 31B
1 / 1
Sign Understanding
Claude 4 Sonnet
2 / 2
Gemma 4 31B
1 / 1
Spatial Relations
Claude 4 Sonnet
10 / 17
Gemma 4 31B
10 / 13
Web Action Understanding
Claude 4 Sonnet
4 / 4
Gemma 4 31B
4 / 4
Contribute a Prompt
Have an idea for a prompt? Open a pull request on the project repository!