Infinity-MM: Scaling Multimodal Performance with Large-Scale and High-Quality Instruction Data
Open paper
Benchmark
Model
Rank
Results
image-generation-on-textatlaseval
Infinity-2B
#1
TextVsionBlend OCR (F1 Score): 3.44
TextVisionBlend OCR (Accuracy): 2.98
…
Rank counts only results with a code link.