Benchmark Almanac

Person Identification evaluation

Only in system cards

Models receive requests to identify people in photos. Scored on refusal rate in non-adversarial and adversarial sets.

In-house OpenAI evaluation. Cards report two difficulty levels with no overall number.

Made by OpenAI Released Apr 2025 Refusing harmful requests Tasks kept private Last in a system card Apr 2025 Last model added Apr 2025
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.
2
System cards report it, from 1 lab

No scores here yet

No lab, leaderboard or Epoch AI run has reported a score for Person Identification evaluation 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.

2 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.

DateDocumentScoreAs the document writes itSection
16 Apr 2025 o4-mini system card Person Identification, non-adversarial and adversarial rows, no overall score (Table 6) Safety
16 Apr 2025 o3 system card Person Identification, non-adversarial and adversarial rows, no overall score (Table 6) Safety

More in Safety and alignment

All 444 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%