benchmarks evals
Mental-Health Evaluation Finds Guidance Calibration Still Fails
MindEval2 combines psychologist-authored criteria with harder synthetic patients and longitudinal memory.
Summary
MindEval2 combines psychologist-authored criteria with harder synthetic patients and longitudinal memory.
Testing 18 proprietary and open-weight models, the authors found that surface quality and boundary behavior improved while guidance calibration remained the dominant source of the quality gap. The framework is an evaluation tool, not clinical validation or a substitute for professional care.
Why it matters
MindEval2 combines psychologist-authored criteria with harder synthetic patients and longitudinal memory.
Limits and context
- The framework is an evaluation tool, not clinical validation or a substitute for professional care.
Key claims
MindEval2 combines psychologist-authored criteria with harder synthetic patients and longitudinal memory.
Qualification: The framework is an evaluation tool, not clinical validation or a substitute for professional care.
Evidence: source-2026-10-16-018
Sources
- arXiv preprint 2610.22314, original v1arXiv / submitting research authors · primary research
Corrections
No corrections have been recorded for this story.