# MentalHealthBench — AI model rankings

overall clinician-rubric score on mental health conversations

2 tracked models have a published MentalHealthBench score. Higher is better. Scores come from published lab reports and benchmark sources; recorded sources appear beside the scores.

## Ranking

| Rank | Model | Developer | Score | Source | Released |
| --- | --- | --- | --- | --- | --- |
| 1 | GPT-6.2 Astra | OpenAI | 53.3% | [OpenAI GPT-6.2 system card](https://deploymentsafety.openai.com/gpt-6-2-astra-sol), retrieved 2026-11-17 | Nov 17 2026 |
| 2 | GPT-6.2 Sol | OpenAI | 50.9% | [OpenAI GPT-6.2 system card](https://deploymentsafety.openai.com/gpt-6-2-astra-sol), retrieved 2026-11-17 | Nov 17 2026 |


---

Canonical page: https://aireleasetracker.com/benchmark/mentalhealthbench
Site index: https://aireleasetracker.com/llms.txt
Source: AI Release Tracker (https://aireleasetracker.com). Most benchmark scores come from lab launch material; gathered results identify the leaderboard that published them.
