OpenAI MentalHealthBench - Behavior - Clinical Accuracy: leaderboard
Behavior axis of OpenAI's MentalHealthBench (launch post and paper, 2026-09-23): reliable, appropriately qualified mental health information, scored on the 853 rubric criteria tagged with this axis. The post's axis score is the signed rubric score on this axis, normalized to its possible range (0-100, higher is better); GPT-5.6 Sol grades, models run at API default reasoning effort. The post's 15 models only: the paper's behavior figure uses a different scale.
Metric: Axis score, normalized to its possible range (%). Source: openai.com. Saturation forecast: Around February 2028. 15 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-6 Astra | 82.6 | #5 |
| 2 | GPT-6 Luna | 80.55 | #90 |
| 3 | GPT-6 Sol | 79.99 | #22 |
| 4 | GPT-5.6 Sol (August 2026) | 76.22 | |
| 5 | Grok 4.7 | 75.33 | #41 |
| 6 | GPT-5.6 Luna (August 2026) | 74.73 | |
| 7 | Muse Spark 1.3 | 71.05 | #45 |
| 8 | Claude Opus 5.5 | 70.69 | #4 |
| 9 | Claude Sonnet 5 | 66.47 | #108 |
| 10 | Claude Fable 5.1 | 66.42 | #13 |
| 11 | GPT-4o (Mar 2025) | 65.69 | #876 |
| 12 | Claude Haiku 4.5 | 64.55 | #593 |
| 13 | Gemini 3.8 Flash | 63.3 | #37 |
| 14 | Gemini 2.5 Pro | 62.08 | #263 |
| 15 | Gemini 3.1 Pro (Preview) | 61.58 | #93 |
No result here: #9 GPT-6.1 Sol, #10 Gemini 4 Argon.
Interactive version: theaggregate.ai/benchmark?slug=openai-mentalhealthbench-behavior-clinical-accuracy · How It Works · Data refreshed daily, snapshot 2026-11-08.