adjustable glasses illustration eye chart illustration clipboard illustration lenses illustration

GPT-4.1 vs.Qwen 3.5 4B

Passed:
GPT-4.1 70.7% (58/82)
Qwen 3.5 4B 63.4% (52/82)
Average request time:
GPT-4.1 12.46s
Qwen 3.5 4B 5.81s

Summary

Annotation Understanding
GPT-4.1 1 / 2
Qwen 3.5 4B 0 / 2
CAPTCHA
GPT-4.1 0 / 2
Qwen 3.5 4B 2 / 2
Color Identification
GPT-4.1 0 / 1
Qwen 3.5 4B 0 / 1
Defect Detection
GPT-4.1 12 / 15
Qwen 3.5 4B 12 / 15
Document Understanding
GPT-4.1 7 / 10
Qwen 3.5 4B 7 / 10
Localization
GPT-4.1 1 / 1
Qwen 3.5 4B 0 / 1
OCR
GPT-4.1 9 / 9
Qwen 3.5 4B 7 / 9
Object Counting
GPT-4.1 2 / 11
Qwen 3.5 4B 4 / 11
Object Detection
GPT-4.1 2 / 2
Qwen 3.5 4B 2 / 2
Object Measurement
GPT-4.1 0 / 1
Qwen 3.5 4B 0 / 1
Object Understanding
GPT-4.1 7 / 11
Qwen 3.5 4B 7 / 11
Receipt Reading
GPT-4.1 1 / 1
Qwen 3.5 4B 1 / 1
Sign Understanding
GPT-4.1 2 / 2
Qwen 3.5 4B 2 / 2
Spatial Relations
GPT-4.1 15 / 17
Qwen 3.5 4B 8 / 17
Web Action Understanding
GPT-4.1 4 / 4
Qwen 3.5 4B 4 / 4

Contribute a Prompt