OpenAI O4 Mini (Medium Reasoning) vs.Mistral Medium 3
Passed:
OpenAI O4 Mini (Medium Reasoning) 79.3% (65/82)
Mistral Medium 3 68.7% (57/83)
Average request time:
OpenAI O4 Mini (Medium Reasoning) 12.87s
Mistral Medium 3 13.13s
Passed:
OpenAI O4 Mini (Medium Reasoning) 79.3% (65/82)
Mistral Medium 3 68.7% (57/83)
Average request time:
OpenAI O4 Mini (Medium Reasoning) 12.87s
Mistral Medium 3 13.13s
Summary
Annotation Understanding
OpenAI O4 Mini (Medium Reasoning)
2 / 2
Mistral Medium 3
1 / 2
CAPTCHA
OpenAI O4 Mini (Medium Reasoning)
2 / 2
Mistral Medium 3
2 / 2
Color Identification
OpenAI O4 Mini (Medium Reasoning)
1 / 1
Mistral Medium 3
0 / 1
Defect Detection
OpenAI O4 Mini (Medium Reasoning)
14 / 15
Mistral Medium 3
12 / 15
Document Understanding
OpenAI O4 Mini (Medium Reasoning)
7 / 10
Mistral Medium 3
8 / 10
Localization
OpenAI O4 Mini (Medium Reasoning)
1 / 1
Mistral Medium 3
1 / 1
OCR
OpenAI O4 Mini (Medium Reasoning)
9 / 9
Mistral Medium 3
9 / 9
Object Counting
OpenAI O4 Mini (Medium Reasoning)
3 / 11
Mistral Medium 3
2 / 11
Object Detection
OpenAI O4 Mini (Medium Reasoning)
1 / 2
Mistral Medium 3
2 / 2
Object Measurement
OpenAI O4 Mini (Medium Reasoning)
0 / 1
Mistral Medium 3
0 / 1
Object Understanding
OpenAI O4 Mini (Medium Reasoning)
10 / 11
Mistral Medium 3
9 / 11
Receipt Reading
OpenAI O4 Mini (Medium Reasoning)
1 / 1
Mistral Medium 3
1 / 1
Sign Understanding
OpenAI O4 Mini (Medium Reasoning)
2 / 2
Mistral Medium 3
2 / 2
Spatial Relations
OpenAI O4 Mini (Medium Reasoning)
15 / 17
Mistral Medium 3
7 / 17
Web Action Understanding
OpenAI O4 Mini (Medium Reasoning)
4 / 4
Mistral Medium 3
4 / 4
Contribute a Prompt
Have an idea for a prompt? Open a pull request on the project repository!