VQAv2

AI benchmark results and model performance

Type: percentageImage To Text

79.20%

78.10% - 80.90%

78.10% - Llama 3.2 90B Vision Instruct

Scores Over Time

Individual benchmark scores plotted by date.

Organisation	Model	Reported	Top Score	Info	Self Reported	Source
Meta	Llama 3.2 90B Vision Instruct	-	78.10%	inferred high-confidence family alias from llama-3.2-90b-instruct (score=0.5873; benches=13)	Yes	Source
Mistral	Pixtral 12B	17 Sept 2024	78.60%	inferred version-family alias from pixtral-12b-2409	Yes	Source
Mistral	Pixtral Large	18 Nov 2024	80.90%	-	Yes	Source