OpenAI O4 Mini (Medium Reasoning) vs.Qwen 3.5 Plus
Passed:
OpenAI O4 Mini (Medium Reasoning) 79.3% (65/82)
Qwen 3.5 Plus 68.3% (56/82)
Average request time:
OpenAI O4 Mini (Medium Reasoning) 12.87s
Qwen 3.5 Plus 4.37s
Passed:
OpenAI O4 Mini (Medium Reasoning) 79.3% (65/82)
Qwen 3.5 Plus 68.3% (56/82)
Average request time:
OpenAI O4 Mini (Medium Reasoning) 12.87s
Qwen 3.5 Plus 4.37s
Summary
Annotation Understanding
OpenAI O4 Mini (Medium Reasoning)
2 / 2
Qwen 3.5 Plus
0 / 2
CAPTCHA
OpenAI O4 Mini (Medium Reasoning)
2 / 2
Qwen 3.5 Plus
2 / 2
Color Identification
OpenAI O4 Mini (Medium Reasoning)
1 / 1
Qwen 3.5 Plus
1 / 1
Defect Detection
OpenAI O4 Mini (Medium Reasoning)
14 / 15
Qwen 3.5 Plus
10 / 15
Document Understanding
OpenAI O4 Mini (Medium Reasoning)
7 / 10
Qwen 3.5 Plus
9 / 10
Localization
OpenAI O4 Mini (Medium Reasoning)
1 / 1
Qwen 3.5 Plus
1 / 1
OCR
OpenAI O4 Mini (Medium Reasoning)
9 / 9
Qwen 3.5 Plus
7 / 9
Object Counting
OpenAI O4 Mini (Medium Reasoning)
3 / 11
Qwen 3.5 Plus
3 / 11
Object Detection
OpenAI O4 Mini (Medium Reasoning)
1 / 2
Qwen 3.5 Plus
0 / 2
Object Measurement
OpenAI O4 Mini (Medium Reasoning)
0 / 1
Qwen 3.5 Plus
1 / 1
Object Understanding
OpenAI O4 Mini (Medium Reasoning)
10 / 11
Qwen 3.5 Plus
9 / 11
Receipt Reading
OpenAI O4 Mini (Medium Reasoning)
1 / 1
Qwen 3.5 Plus
1 / 1
Sign Understanding
OpenAI O4 Mini (Medium Reasoning)
2 / 2
Qwen 3.5 Plus
2 / 2
Spatial Relations
OpenAI O4 Mini (Medium Reasoning)
15 / 17
Qwen 3.5 Plus
11 / 17
Web Action Understanding
OpenAI O4 Mini (Medium Reasoning)
4 / 4
Qwen 3.5 Plus
4 / 4
Contribute a Prompt
Have an idea for a prompt? Open a pull request on the project repository!