ChatGPT-4o (Medium Reasoning) vs.Gemini 3.1 Pro
Passed:
ChatGPT-4o (Medium Reasoning) 75.6% (62/82)
Gemini 3.1 Pro 81.7% (67/82)
Average request time:
ChatGPT-4o (Medium Reasoning) 20.48s
Gemini 3.1 Pro 12.43s
Passed:
ChatGPT-4o (Medium Reasoning) 75.6% (62/82)
Gemini 3.1 Pro 81.7% (67/82)
Average request time:
ChatGPT-4o (Medium Reasoning) 20.48s
Gemini 3.1 Pro 12.43s
Summary
Annotation Understanding
ChatGPT-4o (Medium Reasoning)
1 / 2
Gemini 3.1 Pro
2 / 2
CAPTCHA
ChatGPT-4o (Medium Reasoning)
2 / 2
Gemini 3.1 Pro
2 / 2
Color Identification
ChatGPT-4o (Medium Reasoning)
0 / 1
Gemini 3.1 Pro
1 / 1
Defect Detection
ChatGPT-4o (Medium Reasoning)
12 / 15
Gemini 3.1 Pro
11 / 15
Document Understanding
ChatGPT-4o (Medium Reasoning)
7 / 10
Gemini 3.1 Pro
8 / 10
Localization
ChatGPT-4o (Medium Reasoning)
1 / 1
Gemini 3.1 Pro
1 / 1
OCR
ChatGPT-4o (Medium Reasoning)
9 / 9
Gemini 3.1 Pro
9 / 9
Object Counting
ChatGPT-4o (Medium Reasoning)
3 / 11
Gemini 3.1 Pro
5 / 11
Object Detection
ChatGPT-4o (Medium Reasoning)
2 / 2
Gemini 3.1 Pro
2 / 2
Object Measurement
ChatGPT-4o (Medium Reasoning)
1 / 1
Gemini 3.1 Pro
1 / 1
Object Understanding
ChatGPT-4o (Medium Reasoning)
8 / 11
Gemini 3.1 Pro
11 / 11
Receipt Reading
ChatGPT-4o (Medium Reasoning)
1 / 1
Gemini 3.1 Pro
1 / 1
Sign Understanding
ChatGPT-4o (Medium Reasoning)
2 / 2
Gemini 3.1 Pro
2 / 2
Spatial Relations
ChatGPT-4o (Medium Reasoning)
15 / 17
Gemini 3.1 Pro
12 / 17
Web Action Understanding
ChatGPT-4o (Medium Reasoning)
4 / 4
Gemini 3.1 Pro
4 / 4
Contribute a Prompt
Have an idea for a prompt? Open a pull request on the project repository!