adjustable glasses illustration eye chart illustration clipboard illustration lenses illustration

OpenAI O1 vs.Qwen 2.5 VL 7B

Passed:
OpenAI O1 62.7% (52/83)
Qwen 2.5 VL 7B 55.6% (45/81)
Average request time:
OpenAI O1 49.35s
Qwen 2.5 VL 7B 45.63s

Summary

Annotation Understanding
OpenAI O1 1 / 2
Qwen 2.5 VL 7B 1 / 2
CAPTCHA
OpenAI O1 0 / 2
Qwen 2.5 VL 7B 2 / 2
Color Identification
OpenAI O1 0 / 1
Qwen 2.5 VL 7B 0 / 1
Counting nodes
OpenAI O1 0 / 1
Qwen 2.5 VL 7B 0 / 0
Defect Detection
OpenAI O1 11 / 15
Qwen 2.5 VL 7B 9 / 15
Document Understanding
OpenAI O1 7 / 10
Qwen 2.5 VL 7B 8 / 10
Localization
OpenAI O1 1 / 1
Qwen 2.5 VL 7B 1 / 1
OCR
OpenAI O1 8 / 9
Qwen 2.5 VL 7B 6 / 9
Object Counting
OpenAI O1 2 / 10
Qwen 2.5 VL 7B 1 / 9
Object Detection
OpenAI O1 1 / 2
Qwen 2.5 VL 7B 1 / 2
Object Measurement
OpenAI O1 1 / 2
Qwen 2.5 VL 7B 0 / 2
Object Understanding
OpenAI O1 5 / 11
Qwen 2.5 VL 7B 5 / 11
Receipt Reading
OpenAI O1 1 / 1
Qwen 2.5 VL 7B 0 / 1
Sign Understanding
OpenAI O1 2 / 2
Qwen 2.5 VL 7B 2 / 2
Spatial Relations
OpenAI O1 13 / 17
Qwen 2.5 VL 7B 11 / 17
Web Action Understanding
OpenAI O1 4 / 4
Qwen 2.5 VL 7B 4 / 4

Contribute a Prompt