Claude 3.7 Sonnet vs.GPT-5 (high reasoning)
Passed:
Claude 3.7 Sonnet 63.9% (53/83)
GPT-5 (high reasoning) 73.5% (61/83)
Average request time:
Claude 3.7 Sonnet 13.98s
GPT-5 (high reasoning) 26.96s
Passed:
Claude 3.7 Sonnet 63.9% (53/83)
GPT-5 (high reasoning) 73.5% (61/83)
Average request time:
Claude 3.7 Sonnet 13.98s
GPT-5 (high reasoning) 26.96s
Summary
Annotation Understanding
Claude 3.7 Sonnet
0 / 2
GPT-5 (high reasoning)
1 / 2
CAPTCHA
Claude 3.7 Sonnet
2 / 2
GPT-5 (high reasoning)
0 / 2
Color Identification
Claude 3.7 Sonnet
1 / 1
GPT-5 (high reasoning)
1 / 1
Counting nodes
Claude 3.7 Sonnet
0 / 1
GPT-5 (high reasoning)
0 / 1
Defect Detection
Claude 3.7 Sonnet
10 / 15
GPT-5 (high reasoning)
12 / 15
Document Understanding
Claude 3.7 Sonnet
9 / 10
GPT-5 (high reasoning)
8 / 10
Localization
Claude 3.7 Sonnet
1 / 1
GPT-5 (high reasoning)
1 / 1
OCR
Claude 3.7 Sonnet
7 / 9
GPT-5 (high reasoning)
9 / 9
Object Counting
Claude 3.7 Sonnet
2 / 10
GPT-5 (high reasoning)
3 / 10
Object Detection
Claude 3.7 Sonnet
2 / 2
GPT-5 (high reasoning)
1 / 2
Object Measurement
Claude 3.7 Sonnet
0 / 2
GPT-5 (high reasoning)
0 / 2
Object Understanding
Claude 3.7 Sonnet
7 / 11
GPT-5 (high reasoning)
9 / 11
Receipt Reading
Claude 3.7 Sonnet
1 / 1
GPT-5 (high reasoning)
1 / 1
Sign Understanding
Claude 3.7 Sonnet
2 / 2
GPT-5 (high reasoning)
2 / 2
Spatial Relations
Claude 3.7 Sonnet
9 / 17
GPT-5 (high reasoning)
15 / 17
Web Action Understanding
Claude 3.7 Sonnet
4 / 4
GPT-5 (high reasoning)
4 / 4
Contribute a Prompt
Have an idea for a prompt? Open a pull request on the project repository!