OpenAI O4 Mini (Medium Reasoning) vs.Gemma 4 31B
Passed:
OpenAI O4 Mini (Medium Reasoning) 79.3% (65/82)
Gemma 4 31B 72.2% (39/54)
Average request time:
OpenAI O4 Mini (Medium Reasoning) 12.87s
Gemma 4 31B 15.30s
Passed:
OpenAI O4 Mini (Medium Reasoning) 79.3% (65/82)
Gemma 4 31B 72.2% (39/54)
Average request time:
OpenAI O4 Mini (Medium Reasoning) 12.87s
Gemma 4 31B 15.30s
Summary
Annotation Understanding
OpenAI O4 Mini (Medium Reasoning)
2 / 2
Gemma 4 31B
0 / 1
CAPTCHA
OpenAI O4 Mini (Medium Reasoning)
2 / 2
Gemma 4 31B
2 / 2
Color Identification
OpenAI O4 Mini (Medium Reasoning)
1 / 1
Gemma 4 31B
0 / 0
Defect Detection
OpenAI O4 Mini (Medium Reasoning)
14 / 15
Gemma 4 31B
6 / 8
Document Understanding
OpenAI O4 Mini (Medium Reasoning)
7 / 10
Gemma 4 31B
7 / 7
Localization
OpenAI O4 Mini (Medium Reasoning)
1 / 1
Gemma 4 31B
0 / 1
OCR
OpenAI O4 Mini (Medium Reasoning)
9 / 9
Gemma 4 31B
4 / 4
Object Counting
OpenAI O4 Mini (Medium Reasoning)
3 / 11
Gemma 4 31B
2 / 8
Object Detection
OpenAI O4 Mini (Medium Reasoning)
1 / 2
Gemma 4 31B
1 / 2
Object Measurement
OpenAI O4 Mini (Medium Reasoning)
0 / 1
Gemma 4 31B
0 / 0
Object Understanding
OpenAI O4 Mini (Medium Reasoning)
10 / 11
Gemma 4 31B
4 / 7
Receipt Reading
OpenAI O4 Mini (Medium Reasoning)
1 / 1
Gemma 4 31B
1 / 1
Sign Understanding
OpenAI O4 Mini (Medium Reasoning)
2 / 2
Gemma 4 31B
1 / 1
Spatial Relations
OpenAI O4 Mini (Medium Reasoning)
15 / 17
Gemma 4 31B
10 / 13
Web Action Understanding
OpenAI O4 Mini (Medium Reasoning)
4 / 4
Gemma 4 31B
4 / 4
Contribute a Prompt
Have an idea for a prompt? Open a pull request on the project repository!