adjustable glasses illustration eye chart illustration clipboard illustration lenses illustration

ChatGPT-4o vs.Gemini 2.5 Pro Preview

Passed:
ChatGPT-4o 78.0% (64/82)
Gemini 2.5 Pro Preview 70.7% (58/82)
Average request time:
ChatGPT-4o 13.60s
Gemini 2.5 Pro Preview 18.25s

Summary

Annotation Understanding
ChatGPT-4o 1 / 2
Gemini 2.5 Pro Preview 2 / 2
CAPTCHA
ChatGPT-4o 2 / 2
Gemini 2.5 Pro Preview 2 / 2
Color Identification
ChatGPT-4o 1 / 1
Gemini 2.5 Pro Preview 0 / 1
Counting nodes
ChatGPT-4o 0 / 1
Gemini 2.5 Pro Preview 0 / 1
Defect Detection
ChatGPT-4o 14 / 15
Gemini 2.5 Pro Preview 11 / 15
Document Understanding
ChatGPT-4o 5 / 9
Gemini 2.5 Pro Preview 6 / 9
Find an author
ChatGPT-4o 0 / 1
Gemini 2.5 Pro Preview 0 / 1
Localization
ChatGPT-4o 1 / 1
Gemini 2.5 Pro Preview 1 / 1
OCR
ChatGPT-4o 9 / 9
Gemini 2.5 Pro Preview 9 / 9
Object Counting
ChatGPT-4o 2 / 10
Gemini 2.5 Pro Preview 2 / 10
Object Detection
ChatGPT-4o 2 / 2
Gemini 2.5 Pro Preview 2 / 2
Object Measurement
ChatGPT-4o 1 / 2
Gemini 2.5 Pro Preview 0 / 2
Object Understanding
ChatGPT-4o 9 / 10
Gemini 2.5 Pro Preview 7 / 10
Receipt Reading
ChatGPT-4o 1 / 1
Gemini 2.5 Pro Preview 1 / 1
Sign Understanding
ChatGPT-4o 2 / 2
Gemini 2.5 Pro Preview 2 / 2
Spatial Relations
ChatGPT-4o 16 / 17
Gemini 2.5 Pro Preview 14 / 17
Web Action Understanding
ChatGPT-4o 4 / 4
Gemini 2.5 Pro Preview 4 / 4

Contribute a Prompt