Claude 4 Sonnet vs.OpenAI o3-pro
Passed:
Claude 4 Sonnet 70.7% (58/82)
OpenAI o3-pro 76.8% (63/82)
Average request time:
Claude 4 Sonnet 13.67s
OpenAI o3-pro 39.50s
Passed:
Claude 4 Sonnet 70.7% (58/82)
OpenAI o3-pro 76.8% (63/82)
Average request time:
Claude 4 Sonnet 13.67s
OpenAI o3-pro 39.50s
Summary
Annotation Understanding
Claude 4 Sonnet
1 / 2
OpenAI o3-pro
2 / 2
CAPTCHA
Claude 4 Sonnet
2 / 2
OpenAI o3-pro
0 / 2
Color Identification
Claude 4 Sonnet
1 / 1
OpenAI o3-pro
1 / 1
Counting nodes
Claude 4 Sonnet
0 / 1
OpenAI o3-pro
0 / 1
Defect Detection
Claude 4 Sonnet
12 / 15
OpenAI o3-pro
12 / 15
Document Understanding
Claude 4 Sonnet
6 / 10
OpenAI o3-pro
9 / 10
Localization
Claude 4 Sonnet
0 / 1
OpenAI o3-pro
1 / 1
OCR
Claude 4 Sonnet
7 / 9
OpenAI o3-pro
9 / 9
Object Counting
Claude 4 Sonnet
3 / 10
OpenAI o3-pro
3 / 10
Object Detection
Claude 4 Sonnet
2 / 2
OpenAI o3-pro
2 / 2
Object Measurement
Claude 4 Sonnet
1 / 2
OpenAI o3-pro
0 / 2
Object Understanding
Claude 4 Sonnet
8 / 10
OpenAI o3-pro
8 / 10
Receipt Reading
Claude 4 Sonnet
1 / 1
OpenAI o3-pro
1 / 1
Sign Understanding
Claude 4 Sonnet
2 / 2
OpenAI o3-pro
2 / 2
Spatial Relations
Claude 4 Sonnet
14 / 17
OpenAI o3-pro
15 / 17
Web Action Understanding
Claude 4 Sonnet
4 / 4
OpenAI o3-pro
4 / 4
Contribute a Prompt
Have an idea for a prompt? Open a pull request on the project repository!