adjustable glasses illustration eye chart illustration clipboard illustration lenses illustration

Mistral Small 3.1 24B vs.Qwen 3.5 4B

Passed:
Mistral Small 3.1 24B 44.6% (37/83)
Qwen 3.5 4B 63.4% (52/82)
Average request time:
Mistral Small 3.1 24B 15.16s
Qwen 3.5 4B 5.81s

Summary

Annotation Understanding
Mistral Small 3.1 24B 0 / 2
Qwen 3.5 4B 0 / 2
CAPTCHA
Mistral Small 3.1 24B 2 / 2
Qwen 3.5 4B 2 / 2
Color Identification
Mistral Small 3.1 24B 1 / 1
Qwen 3.5 4B 0 / 1
Defect Detection
Mistral Small 3.1 24B 8 / 15
Qwen 3.5 4B 12 / 15
Document Understanding
Mistral Small 3.1 24B 5 / 10
Qwen 3.5 4B 7 / 10
Localization
Mistral Small 3.1 24B 0 / 1
Qwen 3.5 4B 0 / 1
OCR
Mistral Small 3.1 24B 7 / 9
Qwen 3.5 4B 7 / 9
Object Counting
Mistral Small 3.1 24B 0 / 11
Qwen 3.5 4B 4 / 11
Object Detection
Mistral Small 3.1 24B 1 / 2
Qwen 3.5 4B 2 / 2
Object Measurement
Mistral Small 3.1 24B 0 / 1
Qwen 3.5 4B 0 / 1
Object Understanding
Mistral Small 3.1 24B 4 / 11
Qwen 3.5 4B 7 / 11
Receipt Reading
Mistral Small 3.1 24B 1 / 1
Qwen 3.5 4B 1 / 1
Sign Understanding
Mistral Small 3.1 24B 0 / 2
Qwen 3.5 4B 2 / 2
Spatial Relations
Mistral Small 3.1 24B 6 / 17
Qwen 3.5 4B 8 / 17
Web Action Understanding
Mistral Small 3.1 24B 4 / 4
Qwen 3.5 4B 4 / 4

Contribute a Prompt