adjustable glasses illustration eye chart illustration clipboard illustration lenses illustration

Cohere Aya Vision 32B vs.Phi 4 Multimodal

Passed:
Cohere Aya Vision 32B 56.6% (47/83)
Phi 4 Multimodal 49.4% (41/83)
Average request time:
Cohere Aya Vision 32B 18.49s
Phi 4 Multimodal 15.92s

Summary

Annotation Understanding
Cohere Aya Vision 32B 0 / 2
Phi 4 Multimodal 1 / 2
CAPTCHA
Cohere Aya Vision 32B 0 / 2
Phi 4 Multimodal 0 / 2
Color Identification
Cohere Aya Vision 32B 0 / 1
Phi 4 Multimodal 0 / 1
Counting nodes
Cohere Aya Vision 32B 0 / 1
Phi 4 Multimodal 0 / 1
Defect Detection
Cohere Aya Vision 32B 10 / 15
Phi 4 Multimodal 11 / 15
Document Understanding
Cohere Aya Vision 32B 6 / 10
Phi 4 Multimodal 7 / 10
Localization
Cohere Aya Vision 32B 1 / 1
Phi 4 Multimodal 0 / 1
OCR
Cohere Aya Vision 32B 5 / 9
Phi 4 Multimodal 5 / 9
Object Counting
Cohere Aya Vision 32B 2 / 10
Phi 4 Multimodal 0 / 10
Object Detection
Cohere Aya Vision 32B 2 / 2
Phi 4 Multimodal 2 / 2
Object Measurement
Cohere Aya Vision 32B 0 / 2
Phi 4 Multimodal 0 / 2
Object Understanding
Cohere Aya Vision 32B 8 / 11
Phi 4 Multimodal 5 / 11
Receipt Reading
Cohere Aya Vision 32B 0 / 1
Phi 4 Multimodal 1 / 1
Sign Understanding
Cohere Aya Vision 32B 2 / 2
Phi 4 Multimodal 2 / 2
Spatial Relations
Cohere Aya Vision 32B 10 / 17
Phi 4 Multimodal 7 / 17
Web Action Understanding
Cohere Aya Vision 32B 4 / 4
Phi 4 Multimodal 2 / 4

Contribute a Prompt