Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference
Open paper
Benchmark
Model
Rank
Results
natural-language-understanding-on-glue-dev
ModernBERT Large
#1
GLUE (dev): 90.4
natural-language-understanding-on-glue-dev
ModernBERT Base
#7
GLUE (dev): 88.4
Rank counts only results with a code link.