Search articles by title, topic or section.
Khabre desk
Recent reporting, analysis and explainers from the benchmarking desk.
science
A bioRxiv preprint introduces PLABench, a benchmark comparing nine deep-learning methods for predicting protein–ligand binding affinity. Its authors report that strong overall accuracy did not translate into consistent performance across targets or protein families.
science
A team led by Sandia National Laboratories has developed the QUOPS benchmark, which directly measures the largest computationally relevant quantum circuits a machine can execute and the speed at which it can execute them. Applied to processors from Quantinuum, Google, and IBM, the benchmark revealed a roughly 5-order-of-magnitude gap between current capability and the resource requirements for useful quantum computation.