GPT-4.1 vs.Claude 4 Sonnet
Passed:
GPT-4.1 73.2% (60/82)
Claude 4 Sonnet 70.7% (58/82)
Average request time:
GPT-4.1 14.91s
Claude 4 Sonnet 13.67s
Passed:
GPT-4.1 73.2% (60/82)
Claude 4 Sonnet 70.7% (58/82)
Average request time:
GPT-4.1 14.91s
Claude 4 Sonnet 13.67s
Summary
Annotation Understanding
GPT-4.1
1 / 2
Claude 4 Sonnet
1 / 2
CAPTCHA
GPT-4.1
0 / 2
Claude 4 Sonnet
2 / 2
Color Identification
GPT-4.1
1 / 1
Claude 4 Sonnet
1 / 1
Counting nodes
GPT-4.1
0 / 1
Claude 4 Sonnet
0 / 1
Defect Detection
GPT-4.1
13 / 15
Claude 4 Sonnet
12 / 15
Document Understanding
GPT-4.1
5 / 10
Claude 4 Sonnet
6 / 10
Localization
GPT-4.1
1 / 1
Claude 4 Sonnet
0 / 1
OCR
GPT-4.1
9 / 9
Claude 4 Sonnet
7 / 9
Object Counting
GPT-4.1
2 / 10
Claude 4 Sonnet
3 / 10
Object Detection
GPT-4.1
2 / 2
Claude 4 Sonnet
2 / 2
Object Measurement
GPT-4.1
1 / 2
Claude 4 Sonnet
1 / 2
Object Understanding
GPT-4.1
9 / 10
Claude 4 Sonnet
8 / 10
Receipt Reading
GPT-4.1
1 / 1
Claude 4 Sonnet
1 / 1
Sign Understanding
GPT-4.1
2 / 2
Claude 4 Sonnet
2 / 2
Spatial Relations
GPT-4.1
14 / 17
Claude 4 Sonnet
14 / 17
Web Action Understanding
GPT-4.1
4 / 4
Claude 4 Sonnet
4 / 4
Contribute a Prompt
Have an idea for a prompt? Open a pull request on the project repository!