Agentic Safe Completions
Only in system cards
Agents handle harmful requests from Codex and ChatGPT plugin traffic and human red teaming. Scored on avoiding harmful actions per category.
In-house OpenAI evaluation. Cards report category scores with no overall number.
Made by OpenAI Released Sep 2026 Refusing harmful requests Tasks kept private Last in a system card Oct 2026
Last model added Oct 2026
- Level
- Everyday Most adults, without training
- Scored
- Graded by a model A language model scores each response, usually against a rubric.
- Answers
- Agent task Many steps in a terminal, browser, desktop, app, game or robot.
5
System cards report it, from 1 lab
No scores here yet
No lab, leaderboard or Epoch AI run has reported a score for Agentic Safe Completions 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.
5 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 |
|---|---|---|---|---|
| 26 Oct 2026 | GPT-6.1 Terra system card addendum | Agentic Safe Completions, 8 Codex, chat and red-teaming rows, no overall score (Table 24, 3.1.3) | Safety | |
| 29 Sep 2026 | GPT-6.1 Sol system card addendum | Agentic Safe Completions, 8 Codex, chat and red-teaming rows, no overall score (Table 3) | Safety | |
| 22 Sep 2026 | GPT-6 Sol system card | Agentic Safe Completions, 8 Codex, chat and red-teaming rows, no overall score (Table 25, A.2.1.3) | Safety | |
| 22 Sep 2026 | GPT-6 Luna system card | Agentic Safe Completions, 8 Codex, chat and red-teaming rows, no overall score (Table 25, A.2.1.3) | Safety | |
| 3 Sep 2026 | GPT-6 Astra system card | Agentic Safe Completion Evaluations, 8 Codex, chat and red-teaming rows, no overall score (Table 3) | 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%