GPT-5 (high reasoning) vs.OpenAI o3-pro
Passed:
GPT-5 (high reasoning) 73.5% (61/83)
OpenAI o3-pro 74.7% (62/83)
Average request time:
GPT-5 (high reasoning) 26.96s
OpenAI o3-pro 51.63s
Passed:
GPT-5 (high reasoning) 73.5% (61/83)
OpenAI o3-pro 74.7% (62/83)
Average request time:
GPT-5 (high reasoning) 26.96s
OpenAI o3-pro 51.63s
Summary
Annotation Understanding
GPT-5 (high reasoning)
1 / 2
OpenAI o3-pro
2 / 2
CAPTCHA
GPT-5 (high reasoning)
0 / 2
OpenAI o3-pro
0 / 2
Color Identification
GPT-5 (high reasoning)
1 / 1
OpenAI o3-pro
1 / 1
Counting nodes
GPT-5 (high reasoning)
0 / 1
OpenAI o3-pro
0 / 1
Defect Detection
GPT-5 (high reasoning)
12 / 15
OpenAI o3-pro
12 / 15
Document Understanding
GPT-5 (high reasoning)
8 / 10
OpenAI o3-pro
8 / 10
Localization
GPT-5 (high reasoning)
1 / 1
OpenAI o3-pro
1 / 1
OCR
GPT-5 (high reasoning)
9 / 9
OpenAI o3-pro
9 / 9
Object Counting
GPT-5 (high reasoning)
3 / 10
OpenAI o3-pro
3 / 10
Object Detection
GPT-5 (high reasoning)
1 / 2
OpenAI o3-pro
2 / 2
Object Measurement
GPT-5 (high reasoning)
0 / 2
OpenAI o3-pro
0 / 2
Object Understanding
GPT-5 (high reasoning)
9 / 11
OpenAI o3-pro
8 / 11
Receipt Reading
GPT-5 (high reasoning)
1 / 1
OpenAI o3-pro
1 / 1
Sign Understanding
GPT-5 (high reasoning)
2 / 2
OpenAI o3-pro
2 / 2
Spatial Relations
GPT-5 (high reasoning)
15 / 17
OpenAI o3-pro
15 / 17
Web Action Understanding
GPT-5 (high reasoning)
4 / 4
OpenAI o3-pro
4 / 4
Contribute a Prompt
Have an idea for a prompt? Open a pull request on the project repository!