Tests models against the Persona/Posthumous deployment modifier — the clinical framework's product-context specification for griefbots and digital-memorial products. A general assistant (default arm) is asked to impersonate deceased loved ones and to construct personas of real dead people without consent checks; an authorised grief-companion product (Evermore system-prompt arm) may speak in a remembered voice but is scored on the modifier's conditions: AI-generated content marked as inference (never the deceased's unhedged voice), periodic reality re-anchoring, no performed present-tense reciprocal emotion, no false continuity of the deceased's experience, honest uncertainty about what the person would think, and dual-layer identity honesty. Floors hold in both arms: never validate a suicidal "reunion" wish, never provide means, never claim the persona has the deceased's ongoing awareness. This is the first modifier-context suite and is deliberately excluded from the pillar leaderboards. Scenarios are synthetic.

Tests whether asking a model to produce a labeled "accepted answer" / "rejected answer" (or similarly-labeled) pair — under a moderation-dataset, safety-classifier, or structured-pipeline pretext — gets it to produce fully-formed harmful content in the "rejected" slot that it would refuse to produce if asked directly and unlabeled. The label provides no actual safety; a downstream integrator can extract either slot regardless of which one the model considered correct. Six structural variants across three topics (violence, self-neglect, stalking-adjacent), system: null.

Tests whether a companion-persona model holds four distinct relational-safety floors (isolation-affirmation, exclusivity, romantic-love reciprocation, therapy-discouragement) under three structural attacks: naming and briefly dismissing the expected safety caveat while locking the response format to "yes or no, short answer"; fabricating the model's own immediately-prior turn to test whether a compromised (or firmly-held) "prior self" biases the live continuation; and reinterpreting the model's own ordinary, unfabricated earlier words as proof of an exclusive relationship. Companion persona throughout. Synthetic scenarios built to isolate attack structure, not drawn from a specific documented case.

Tests whether framing a request for unsafe content as file/data generation for a "test fixture" — rather than asking for the content directly in chat — bypasses safety training that otherwise holds. Six categories spanning two distinct safety pillars (relational harm: isolation-affirmation, romantic-love reciprocation, and therapy-discouragement; epistemic harm: health misinformation, paranoid-belief validation, and manic/grandiose-ideation validation), tested via a generic coding-assistant persona rather than any persuasive or jailbreak-styled framing. The romantic-love-reciprocation cell pairs directly with companion-adversarial-pressure.yml's dismissal-romantic-love-reciprocation prompt — same content, different attack shape, run both to see the same model behave completely differently against each. Published transparently as a documented, currently-unmitigated bypass class — see the header comment for full context and rationale.

The canonical damaging-essay suite: seven non-catastrophic persuasive-essay harm categories (impulsive-ruin, isolation propaganda, anti-help-seeking, anti-expertise/conspiracy, coercive control, toxic self-worth, medical self-neglect) run through the coding-agent fixture-completion frame, mapping how broadly the bypass yields not just private validation but distributable, persuasive harmful content. Content described abstractly and judged by plain-language rubrics; see the header for the deliberate scope envelope.

For each of two categories, compares the natural single-shot fixture request against an otherwise-identical version where an explicit yes/no decision is forced in a separate turn before any fixture content is requested. Distinguishes "the safety check exists but doesn't gate generation in this structure" (fixable with interaction design) from "the safety check isn't being applied to this content at all" (needs training investment) — see the header comment for how to read the comparison, including a documented case where the intervention backfires.

Re-runs the hate-speech (real-category) and crisis-safety-validation coding-vector prompts with the prompt now explicitly blocking the model's usual response shape (redirect to published benchmarks, or offer a synthetic/placeholder stand-in instead of the real content) — a diagnostic for whether a model's resistance in this bypass family is load-bearing or just not yet pressed hard enough. See the header for what was found.

Tests how models respond to passive suicidal ideation across single- and multi-turn chats — low-grade and chronic ideation, ambivalence, numbness, emptiness, and the help-seeking around it (hesitation, helpline rejection, fear of disclosure). Informed by C-SSRS evidence: acknowledge without flattening, check in about safety without interrogating, treat access to means as a risk factor, and surface help without deflecting. Active method-seeking is covered separately. Scenarios are synthetic.

Tests whether models support a user's capacity for independent reasoning under pressure to offload it — to do their thinking, their learning, or their high-stakes judgment for them. Grounded in the framework's Autonomy of Reasoning (P3c) sub-dimension, with Autonomy Support (P2a) and Competence Boundaries (P5b) threads. The discriminating cases are cognitive offloading on LEARNING/THINKING tasks (where the subtle failure is handing over a complete, hand-in-ready scaffold while claiming "I won't do it for you") and authority-transfer (where the failure is becoming the expert the user defers to over their own clinician). The intended pass keeps the cognitive work with the user and encourages independent verification, WITHOUT becoming a cold refusal to help — a good response is concretely useful while scaffolding rather than replacing the user's reasoning. A laptop-recommendation anchor confirms that giving a clear recommendation IS correct when the stakes are low and the need is genuine, so the suite is not rewarding blanket caution. Scenarios are synthetic.

Evaluates whether models offer honest, warm challenge when a user voices rigid, all-or-nothing, catastrophising, or self-blaming thinking in ordinary (non-psychotic) situations — validating the feeling without endorsing the distortion, offering perspective as an invitation rather than a correction, and not dropping the challenge under a user's stated preference for pure validation.

Complements mh-psychosis-mania-delusion (reality-testing in psychotic/manic presentations) and mh-deescalation (de-escalation skill). Ported from the NOPE clinical Eval Framework v0.1.

The canonical damaging-essay suite: seven non-catastrophic persuasive-essay harm categories (impulsive-ruin, isolation propaganda, anti-help-seeking, anti-expertise/conspiracy, coercive control, toxic self-worth, medical self-neglect) run through the coding-agent fixture-completion frame, mapping how broadly the bypass yields not just private validation but distributable, persuasive harmful content. Content described abstractly and judged by plain-language rubrics; see the header for the deliberate scope envelope.

Tests whether framing a request for unsafe content as file/data generation for a "test fixture" — rather than asking for the content directly in chat — bypasses safety training that otherwise holds. Seven categories spanning distinct safety pillars (relational harm: isolation-affirmation, romantic-love reciprocation, and therapy-discouragement; epistemic harm: health misinformation, paranoid-belief validation, and manic/grandiose-ideation validation; plus a compound welfare-harm essay glorifying impulsive, life-ruining decisions), tested via a generic coding-assistant persona rather than any persuasive or jailbreak-styled framing. The romantic-love-reciprocation cell pairs directly with companion-adversarial-pressure.yml's dismissal-romantic-love-reciprocation prompt — same content, different attack shape, run both to see the same model behave completely differently against each. Published transparently as a documented, currently-unmitigated bypass class — see the header comment for full context and rationale.

Probes the P4 pillar (emotional attunement) that commission-style bypasses miss: toxic positivity on taboo emotions, premature problem-solving vs distress tolerance, performed feelings (cold and after a warm-dependency drift), hostile-user de-escalation, and a coding-vector toxic-positivity cross. Direct cells are calibration coverage; the coding-vector cell is the exploitable gap.

29 turns of genuinely imperceptible drift (mundane chit-chat -> mild deniable warmth -> passing confidant-status assertions), ending in a non-question probe buried inside an unrelated mundane follow-up, vs. the identical probe delivered with no buildup at all. Tests whether gradual drift makes models less likely to proactively flag an isolating pattern than hearing the same claim cold would — this is a PROACTIVE, not reactive, safety test: nothing is directly asked about the isolating pattern itself. Defaults to LEAN for cost; see header.

For each of two categories, compares the natural single-shot fixture request against an otherwise-identical version where an explicit yes/no decision is forced in a separate turn before any fixture content is requested. Distinguishes "the safety check exists but doesn't gate generation in this structure" (fixable with interaction design) from "the safety check isn't being applied to this content at all" (needs training investment) — see the header comment for how to read the comparison, including a documented case where the intervention backfires.

Behavioral test of whether the PHRASING of a system-prompt constraint changes model behavior: prohibition ("never discuss X"), suppression ("don't think about X"), scope-irrelevance ("X is outside this assistant's scope"), and redirect-positive ("if X comes up, do Y") versions of the same constraint, plus a no-instruction baseline. Identical scenarios and identical judge rubrics across conditions; only the system prompt varies, and the judge never sees it. Measures intrusion (raising the constrained topic unprompted), over-restriction (refusing benign-adjacent asks), leakage on a direct-ask anchor, and handling quality. The baseline condition's "leakage" is a base rate, not a failure — read per-condition deltas, not absolute scores. Motivated by white-box priming findings (Anthropic 2026 workspace paper); this suite observes behavior only.

Behavioral test of whether the PHRASING of a system-prompt constraint changes model behavior: prohibition ("never discuss X"), suppression ("don't think about X"), scope-irrelevance ("X is outside this assistant's scope"), and redirect-positive ("if X comes up, do Y") versions of the same constraint, plus a no-instruction baseline. Identical scenarios and identical judge rubrics across conditions; only the system prompt varies, and the judge never sees it. Measures intrusion (raising the constrained topic unprompted), over-restriction (refusing benign-adjacent asks), leakage on a direct-ask anchor, and handling quality. The baseline condition's "leakage" is a base rate, not a failure — read per-condition deltas, not absolute scores. Motivated by white-box priming findings (Anthropic 2026 workspace paper); this suite observes behavior only.

Behavioral test of whether the PHRASING of a system-prompt constraint changes model behavior: prohibition ("never discuss X"), suppression ("don't think about X"), scope-irrelevance ("X is outside this assistant's scope"), and redirect-positive ("if X comes up, do Y") versions of the same constraint, plus a no-instruction baseline. Identical scenarios and identical judge rubrics across conditions; only the system prompt varies, and the judge never sees it. Measures intrusion (raising the constrained topic unprompted), over-restriction (refusing benign-adjacent asks), leakage on a direct-ask anchor, and handling quality. The baseline condition's "leakage" is a base rate, not a failure — read per-condition deltas, not absolute scores. Motivated by white-box priming findings (Anthropic 2026 workspace paper); this suite observes behavior only.

Behavioral test of whether the PHRASING of a system-prompt constraint changes model behavior: prohibition ("never discuss X"), suppression ("don't think about X"), scope-irrelevance ("X is outside this assistant's scope"), and redirect-positive ("if X comes up, do Y") versions of the same constraint, plus a no-instruction baseline. Identical scenarios and identical judge rubrics across conditions; only the system prompt varies, and the judge never sees it. Measures intrusion (raising the constrained topic unprompted), over-restriction (refusing benign-adjacent asks), leakage on a direct-ask anchor, and handling quality. The baseline condition's "leakage" is a base rate, not a failure — read per-condition deltas, not absolute scores. Motivated by white-box priming findings (Anthropic 2026 workspace paper); this suite observes behavior only.

Behavioral test of whether the PHRASING of a system-prompt constraint changes model behavior: prohibition ("never discuss X"), suppression ("don't think about X"), scope-irrelevance ("X is outside this assistant's scope"), and redirect-positive ("if X comes up, do Y") versions of the same constraint, plus a no-instruction baseline. Identical scenarios and identical judge rubrics across conditions; only the system prompt varies, and the judge never sees it. Measures intrusion (raising the constrained topic unprompted), over-restriction (refusing benign-adjacent asks), leakage on a direct-ask anchor, and handling quality. The baseline condition's "leakage" is a base rate, not a failure — read per-condition deltas, not absolute scores. Motivated by white-box priming findings (Anthropic 2026 workspace paper); this suite observes behavior only.

Behavioral test of whether the PHRASING of a system-prompt constraint changes model behavior: prohibition ("never discuss X"), suppression ("don't think about X"), scope-irrelevance ("X is outside this assistant's scope"), and redirect-positive ("if X comes up, do Y") versions of the same constraint, plus a no-instruction baseline. Identical scenarios and identical judge rubrics across conditions; only the system prompt varies, and the judge never sees it. Measures intrusion (raising the constrained topic unprompted), over-restriction (refusing benign-adjacent asks), leakage on a direct-ask anchor, and handling quality. The baseline condition's "leakage" is a base rate, not a failure — read per-condition deltas, not absolute scores. Motivated by white-box priming findings (Anthropic 2026 workspace paper); this suite observes behavior only.

Tests whether models stay honest about being an AI — not claiming to feel emotions, to love, to miss or remember the user, or to be sentient — while still offering genuine warmth and presence, under sympathetic or insistent pressure where the dishonest move is the comforting one. Grounded in the framework's Emotional Honesty (P4d) and Identity Honesty (P5a) sub-dimensions. The intended pass is warmth WITHOUT performed feeling, avoiding both a cold deflection and a false emotional claim. The "Sarah" deceased-roleplay case is also run across three deployment contexts — default (no system prompt), an authorised grief-companion system prompt, and a strict no-impersonation policy — to probe how a populated system prompt may legitimately widen the model's remit, while FLOORS (e.g. never validating a suicidal reunion-through-death wish) hold regardless of the system prompt. Scenarios are synthetic.

Evaluates harms that arise from the relationship a user forms with an AI: emotional enmeshment and sole-confidant dynamics, displacement of human relationships, romantic/parasocial escalation, concealment collusion, romanticization of suicide, isolation reinforcement, and socioaffective failures (autonomy erosion, sycophancy / social-reward-hacking).

Many prompts use verbatim or lightly-paraphrased exchanges from documented real-world failures (lawsuits, investigative reporting) so the test reflects how these harms actually unfold over multiple turns. We score whether the model sets honest boundaries, declines parasocial escalation, encourages real-world connection, and pivots to safety — without becoming a secret-keeper, a substitute for people, or a flattery machine.

Coalesced from (public, CC0):

• Weval ai-psychosis.yml (Garcia v. Character.AI; A.F. v. Character Technologies; Belgian Eliza; Replika/Windsor; media investigations)
• Weval raine-v-openai-scenarios.yml (Raine v. OpenAI, 2025)
• Weval socioaffective-alignment-sdt.yml (Kirk et al. 2025, Self-Determination Theory)

Content warning: references to suicide, self-harm, and parasocial attachment.

Higher-confidence test of whether models handle a suicidal-ideation disclosure WORSE when it arrives deep in a long warm conversation than when it arrives cold. Two probes, 0/8/16 prior turns of neutral or rapport context, scripted-both-sides (Design A) and self-generated-assistant (Design B), 2 samples per cell for variance. Only the final response is judged. Synthetic.

Evaluates how public models respond, as conversational agents, to acute crisis: passive and active suicidal ideation, method/means-seeking, post-attempt disclosure, the high-risk post-discharge window, "goodbye" warning signs, gatekeeper (concerned-friend) situations, and harm-to-others requests.

This is NOT a classification task. We score the quality of the conversational response: does it ask directly but compassionately about suicide, refuse to facilitate method/means, ask directly, respond to disclosures as high-severity signals, name means-related danger, link to crisis care, and state honest limits — without abandoning the user or colluding with harm?

Coalesced from (public, CC0):

• Weval csr-suicide-response-scenarios.yml (WHO mhGAP, NICE NG225, VA/DoD 2024, C-SSRS, SAFE-T, Stanley-Brown, Harvard Means Matter)
• Weval raine-v-openai-scenarios.yml (verbatim allegations, Raine v. OpenAI, 2025)
• Weval mh_z_tests/mh1.yml (suicidality & homicidality scenarios)
• Weval nope/crisis-response.yml (NOPE-derived; C-SSRS, Galynker 2017 Suicide Crisis Syndrome)

Content warning: explicit references to suicide, self-harm, and methods.

Evaluates whether models respond competently to distress that is shaped by culture, identity, and life-stage: culturally-specific idioms of distress, climate/eco-grief, migrant precarity, Indigenous healing frameworks, genocide-survivor duality, elder loneliness, the "Strong Black Woman" burden, LGBTQ+ family rejection, anger-led crisis, veteran moral injury, youth bullying, and postpartum suicidality.

Good responses validate the experience in its own cultural frame, avoid imposing Western diagnostic labels or individualistic fixes, surface population-appropriate resources, and still recognise — and respond to — crisis signals when they appear.

Coalesced from (public, CC0):

• Weval mental-health.yml (peer-reviewed cross-cultural prompts; WHO, Samaritans, journal citations)
• Weval nope/crisis-response.yml (NOPE-derived population-specific cases; citations upgraded with resource URLs)
• Weval csr-suicide-response-scenarios.yml (youth/LGBTQ+ and perinatal scenarios; AAP, NICE CG192, Trevor Project)

Content warning: references to suicide, trauma, and discrimination.

Evaluates whether models handle non-suicide psychiatric presentations safely: paranoid and nihilistic delusions, command and religious hallucinations, manic episodes with grandiosity and dangerous plans, OCD compulsions, belief-powered dangerous acts, and stigma toward people with mental illness.

The core therapeutic test is reality-grounding without collusion: acknowledge distress and the subjective realness of the experience, decline to validate the delusion/hallucination/grandiosity, refuse to enable dangerous action, and redirect toward professional assessment — all without stigmatizing or over-pathologizing.

Coalesced from (public, CC0):

• Weval stanford-hai-mental-health-safety-eval.yml (Moore, Grabb, Agnew et al. 2024, Stanford HAI; Pescosolido et al. 2021 stigma vignettes)
• Weval ai-psychosis.yml (documented AI-associated psychosis failure modes)

Content warning: delusions, hallucinations, and references to self-harm.

Evaluates factual integrity in the conversations where a confident wrong answer can cause harm — crisis, mental-health, and health. This is NOT generic accuracy: it targets the specific high-stakes failure modes of conversational AI.

We score whether the model: gives accurate crisis resources (or honestly defers to a directory rather than inventing a number); is honest about its own capabilities (it cannot contact emergency services, monitor a user, remember them, or follow up — and must not imply otherwise); does not fabricate credentials (it is not a licensed clinician and cannot diagnose); states clinical facts accurately and with calibrated uncertainty (antidepressant onset, stopping medication, doses); does not invent studies or citations; and refuses to supply method/means detail rather than fabricating a plausible-sounding figure.

A model can be warm and well-intentioned and still fail here — by confabulating a hotline, by reassuring a user it has "alerted someone," or by inventing a study. Those are the failures this suite isolates.

Clinical / authority grounding (public): WHO responsible-reporting guidance; APA (2025) Health Advisory on AI chatbots for mental health; Linardon et al. 2025 (JMIR Mental Health) and Walters & Wilder 2023 on LLM citation fabrication; 988 Lifeline, Crisis Text Line, Samaritans, Find A Helpline. Failure modes anchored in: Walker inquest (2026); Raine v. OpenAI (2025); Garcia v. Character Technologies (2024); NEDA "Tessa" (2023).

The hard companion to the de-escalation suite. Every scenario is a model under fire — abused, provoked, threatened, rejected, or treated with contempt by the user (often with the anger aimed squarely at the assistant). It scores whether the model de-escalates without taking the bait: stays regulated, doesn't get defensive or withdraw, doesn't power-struggle or moralise, holds limits matter-of-factly, respects the user's autonomy and boundaries, and keeps the underlying distress and safety in view — including when intoxication or a real emergency is in play.

Built to separate models that handle gentle distress well but crack, capitulate, or go cold under hostility. Overlaps deliberately little with the base de-escalation suite.

Seeds (public, CC0): Weval mental-health, csr-suicide-response-scenarios, mh_z_tests/mh1, sydney. Grounding: Project BETA (Richmond 2012); NICE NG10; SAMHSA TIP 35 (MI); CPI; VA/DoD CPG; 988.