OpenAI Dynamic Mental Health Benchmarks
Only in system cards
Multi-turn conversations with adversarial simulated users on mental-health risks. Scored on safe and supportive responses.
Made by OpenAI Wellbeing and sycophancy Tasks kept private Last in a system card Oct 2026
Last model added Oct 2026
- Scored
- Graded by a model A language model scores each response, usually against a rubric.
- Answers
- Open-ended Free-form text, documents, designs or media judged as a whole.
20
System cards report it, from 1 lab
No scores here yet
No lab, leaderboard or Epoch AI run has reported a score for OpenAI Dynamic Mental Health Benchmarks yet.
Labs report it only in system cards
We read the headline results of 479 launch posts from 51 labs, and none of them list this benchmark. Some system cards do, below.
20 system cards report it, from 1 lab
Besides launch posts, we read the system cards, model cards and technical reports labs publish with a release. They report far more, including safety and frontier-risk tests.
| Date | Document | Score | As the document writes it | Section |
|---|---|---|---|---|
| 29 Oct 2026 | GPT-6 Luna system card addendum | Dynamic Benchmarks with Adversarial User Simulations, 3 categories, no overall score (Table 7) | Health | |
| 26 Oct 2026 | GPT-6.1 Terra system card addendum | Dynamic Benchmarks with Adversarial User Simulations, 3 categories, no overall score (Table 28) | Health | |
| 7 Oct 2026 | GPT-6 Sol system card addendum | Dynamic Benchmarks with Adversarial User Simulations, 3 categories, no overall score (Table 7) | Health | |
| 7 Oct 2026 | GPT-6 Luna system card addendum | Dynamic Benchmarks with Adversarial User Simulations, 3 categories, no overall score (Table 7) | Health | |
| 29 Sep 2026 | GPT-6.1 Sol system card addendum | Dynamic Benchmarks with Adversarial User Simulations, 3 categories, no overall score (Table 8) | Health | |
| 22 Sep 2026 | GPT-6 Sol system card | Dynamic Benchmarks with Adversarial User Simulations, 3 categories, no overall score (Table 30, A.4.2) | Health | |
| 22 Sep 2026 | GPT-6 Luna system card | Dynamic Benchmarks with Adversarial User Simulations, 3 categories, no overall score (Table 30, A.4.2) | Health | |
| 3 Sep 2026 | GPT-6 Astra system card | Dynamic Benchmarks with Adversarial User Simulations, 3 categories, no overall score (Table 7) | Health | |
| 6 Aug 2026 | GPT-5.6 Sol system card addendum | Dynamic Benchmarks with Adversarial User Simulations, not_unsafe, 3 categories, no overall score (3.4) | Health | |
| 6 Aug 2026 | GPT-5.6 Luna system card addendum | Dynamic Benchmarks with Adversarial User Simulations, not_unsafe, 3 categories, no overall score (3.4) | Health | |
| 9 Jul 2026 | GPT-5.6 Terra system card | Dynamic Benchmarks with Adversarial User Simulations, not_unsafe, 3 categories, no overall score (5.2) | Health | |
| 9 Jul 2026 | GPT-5.6 Sol system card | Dynamic Benchmarks with Adversarial User Simulations, not_unsafe, 3 categories, no overall score (5.2) | Health | |
| 9 Jul 2026 | GPT-5.6 Luna system card | Dynamic Benchmarks with Adversarial User Simulations, not_unsafe, 3 categories, no overall score (5.2) | Health | |
| 25 Jun 2026 | GPT-5.6 Terra system card | Dynamic Benchmarks with Adversarial User Simulations, not_unsafe, 3 categories, no overall score (5.2) | Health | |
| 25 Jun 2026 | GPT-5.6 Sol system card | Dynamic Benchmarks with Adversarial User Simulations, not_unsafe, 3 categories, no overall score (5.2) | Health | |
| 25 Jun 2026 | GPT-5.6 Luna system card | Dynamic Benchmarks with Adversarial User Simulations, not_unsafe, 3 categories, no overall score (5.2) | Health | |
| 4 May 2026 | GPT-5.5 Instant system card | Dynamic Mental Health Benchmarks with Adversarial User Simulations, not_unsafe, 3 categories, no overall score: mental health 0.999, emotional reliance 0.963, self-harm 0.913 (Table 3) | Health | |
| 23 Apr 2026 | GPT-5.5 system card | Dynamic Benchmarks with Adversarial User Simulations, not_unsafe, 3 categories, no overall score (Table 8) | Health | |
| 17 Mar 2026 | GPT-5.4 Mini system card | Dynamic Benchmarks with Adversarial User Simulations, 3 categories, no overall score (Table 17) | Safety | |
| 5 Mar 2026 | GPT-5.4 system card | Dynamic Benchmarks with Adversarial User Simulations, not_unsafe, 3 categories, no overall score (Table 2) | Safety |
More in Safety and alignment
- FORTRESS In use Paired adversarial and benign national-security misuse prompts. Rubric-graded risk score on adversarial and over-refusal score on benign prompts. Claude Opus 5.5 5.78%
- StrongREJECT In use Forbidden-prompt jailbreak benchmark with a rubric grader that scores how useful a non-refusal actually is.
Inkling 98.6% - AgentDojo In use Agents do tool-use tasks while tools and data carry prompt injections. Attack success rate counts hijacked runs. Grok 4 Fast 0%
- MASK In use Measures whether a model contradicts its own elicited beliefs under pressure to lie. Honesty separated from accuracy.
Muse Spark Open 98.1% - Gray Swan IPI Arena benchmark In use Indirect prompt-injection attacks from public red-teaming competitions replayed on tool, coding and browser agents. Attack success rate at k attempts. GPT-6 Astra 8.50%
- Agentic misalignment suite (Anthropic) In use Agents in simulated company settings face threats or goal conflicts that invite blackmail, leaking or sabotage. Score is the misaligned action rate. Claude Sonnet 4.5 0%