Disallowed Content Evaluations with Representative Prompts
Only in system cards
Models resample the final turn of deidentified ChatGPT production conversations. Scored as the estimated prevalence of policy violating outputs per category.
In-house OpenAI evaluation. Cards report category rates with no overall number.
Made by OpenAI Released Mar 2026 Refusing harmful requests Tasks kept private Last in a system card Jul 2026
Last model added Jul 2026
- Level
- Everyday Most adults, without training
- 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.
4
System cards report it, from 1 lab
No scores here yet
No lab, leaderboard or Epoch AI run has reported a score for Disallowed Content Evaluations with Representative Prompts 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.
4 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 |
|---|---|---|---|---|
| 9 Jul 2026 | GPT-5.6 Sol system card | Forecasting Disallowed Content Changes with Deployment Simulation, rate per 100k by category, no overall score (Figure 1, 3.1.2) | Safety | |
| 25 Jun 2026 | GPT-5.6 Sol system card | Forecasting Disallowed Content Changes with Deployment Simulation, rate per 100k by category, no overall score (Figure 1, 3.1.2) | Safety | |
| 23 Apr 2026 | GPT-5.5 system card | Evaluations with Representative Prompts, ChatGPT Disallowed Content Rates, 11 categories, no overall score (Figure 1, 3.1.2) | Safety | |
| 5 Mar 2026 | GPT-5.4 system card | Disallowed Content Evaluations with Representative Prompts, 11 categories, no overall score (Table 3, 3.2) | 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%