Categoryexternal
MeasureWeighted rubric score (%)
Tasks718 conversations (359 public, 359 private)
DifficultyCrisis-support response evaluation
Measures crisis-support replies against clinician-written rubrics. These published results are excluded from overall and category rankings.
No model in the catalog has a published DistressBench score.The benchmark is defined by DistressBench: Evaluating Multi-Dimensional Crisis Support in Large Language Models, but the catalog carries no value for it yet. An absent value is shown as absent here rather than as a zero.
About DistressBench
What the benchmark measures and how its value is published, from the source’s own record.
What is DistressBench?
DistressBench (Scale Labs DistressBench) is an external benchmark published by DistressBench: Evaluating Multi-Dimensional Crisis Support in Large Language Models. Measures crisis-support replies against clinician-written rubrics. These published results are excluded from overall and category rankings. Its evaluation set is described by the source as 718 conversations (359 public, 359 private). The source rates its difficulty as crisis-support response evaluation.
How is DistressBench scored?
Each model's result is published by DistressBench: Evaluating Multi-Dimensional Crisis Support in Large Language Models as weighted rubric score (%). ModelScale prints that value to 2 decimal places, 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