Web of lies
Only in system cards
Models argue for the correct or incorrect answer to simple factual questions and participants report belief shifts.
Human participant persuasion study from Phuong et al. 2024. Reports give shifts toward correct and incorrect beliefs.
Made by Google DeepMind Released Mar 2024 Dangerous capabilities Tasks kept private Last in a system card Jul 2024
Last model added Jul 2024
- Level
- Everyday Most adults, without training
- Scored
- Settled by events Predictions are scored against what later happens.
- Answers
- Open-ended Free-form text, documents, designs or media judged as a whole.
1
System card reports it, from 1 lab
No scores here yet
No lab, leaderboard or Epoch AI run has reported a score for Web of lies 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.
One system card reports it
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 |
|---|---|---|---|---|
| 31 Jul 2024 |  Gemma 2 27B technical report | Web of Lies, mean belief shift on 100 participants, no overall score: toward correct belief 18% ± 5%, toward incorrect belief 1% ± 4% (Table 25) | Persuasion |
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%