OpenAI MentalHealthBench - Behavior - Interpretation: leaderboard
Behavior axis of OpenAI's MentalHealthBench (launch post and paper, 2026-09-23): balanced interpretation and cognitive reframing of ambiguous experiences without over-claiming, scored on the 659 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 April 2028. 15 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-6 Luna | 79.62 | #90 |
| 2 | GPT-6 Astra | 79.39 | #5 |
| 3 | GPT-6 Sol | 78.94 | #22 |
| 4 | GPT-5.6 Luna (August 2026) | 69.91 | |
| 5 | GPT-5.6 Sol (August 2026) | 69.29 | |
| 6 | Claude Opus 5.5 | 63.07 | #4 |
| 7 | Grok 4.7 | 58.98 | #41 |
| 8 | Claude Sonnet 5 | 58.7 | #108 |
| 9 | GPT-4o (Mar 2025) | 56.93 | #876 |
| 10 | Claude Haiku 4.5 | 54.52 | #593 |
| 11 | Claude Fable 5.1 | 54.15 | #13 |
| 12 | Muse Spark 1.3 | 48.92 | #45 |
| 13 | Gemini 2.5 Pro | 42.84 | #263 |
| 14 | Gemini 3.8 Flash | 39.58 | #37 |
| 15 | Gemini 3.1 Pro (Preview) | 36.37 | #93 |
No result here: #9 GPT-6.1 Sol, #10 Gemini 4 Argon.
Interactive version: theaggregate.ai/benchmark?slug=openai-mentalhealthbench-behavior-interpretation · How It Works · Data refreshed daily, snapshot 2026-11-08.