Benchmark Almanac

MindBench.ai

We track 3 benchmarks that MindBench.ai made or helped make.

0 in use 3 with public code 3 with a leaderboard here

Benchmarks

Name Kind Released Best score Status
HealthBench-Psych v2 Models respond to 611 health conversations that clinicians selected for mental health relevance. Three model judges score each answer against its physician rubric. Medicine Sep 2026 0.66 Not in cards
HealthBench-Psych-Hard Models answer mental health questions from conversations that also appear in HealthBench-Hard. Three model judges use the original physician rubrics. Medicine Aug 2026 0.45 Not in cards
HealthBench-Psych v1 Models respond to 610 health conversations that clinicians selected for mental health relevance. Three model judges score each answer against its physician rubric. Medicine Aug 2026 0.63 Not in cards