Knowledge benchmark
HealthBench Professional (length-adjusted, Artificial Analysis) leaderboard
Artificial Analysis HealthBench Professional length-adjusted score. Every model the catalog carries a published HealthBench Professional (length-adjusted, Artificial Analysis) value for, ranked by that value.
CategoryKnowledge
MeasureLength-adjusted rubric score
Tasks525 conversations
DifficultyHealth conversation evaluation
Artificial Analysis independently evaluates 525 conversations and reports a length-adjusted rubric score.
No model in the catalog has a published HealthBench Professional (length-adjusted, Artificial Analysis) score.The benchmark is defined by HealthBench Professional independent evaluation, but the catalog carries no value for it yet. An absent value is shown as absent here rather than as a zero.
About HealthBench Professional (length-adjusted, Artificial Analysis)
What the benchmark measures and how its value is published, from the source’s own record.
What is HealthBench Professional (length-adjusted, Artificial Analysis)?
HealthBench Professional (length-adjusted, Artificial Analysis) (Artificial Analysis HealthBench Professional length-adjusted score) is a knowledge benchmark published by HealthBench Professional independent evaluation. Artificial Analysis independently evaluates 525 conversations and reports a length-adjusted rubric score. Its evaluation set is described by the source as 525 conversations. The source rates its difficulty as health conversation evaluation.
How is HealthBench Professional (length-adjusted, Artificial Analysis) scored?
Each model's result is published by HealthBench Professional independent evaluation as length-adjusted rubric score. ModelScale prints that value to 1 decimal place, exactly as published, and never converts or rescales it. This page ranks the 0 models that carry a published value, highest value first; a model the source never scored is left out rather than ranked at zero. The source does not state whether a higher value is the better result, so neither does this page.
ModelScale