BEND 2.0 benchmark evaluates DNA language models
New benchmark tests genomic foundation models on eight tasks for predicting DNA edit effects and guiding sequence design.
4 stories, newest first · one card per story
New benchmark tests genomic foundation models on eight tasks for predicting DNA edit effects and guiding sequence design.

The announcement frames Carbon-X as an open model that jointly handles DNA sequences and natural language.
The open chat model, started from Qwen3-14B, reports 66.7% on five DNA benchmarks with thinking disabled.
ICE's DNA collection program projects detainee samples to reach 33% of CODIS offender index by 2030, raising privacy concerns.
Today 1.6K readers · 2.4K views · 775 reads · all time 189K views