Malicious agentic influence campaigns, 34-point rubric (Anthropic)
Agents run simulated voter suppression and domestic polarization campaigns. Weighted criteria measure campaign execution on a 34-point scale.
Anthropic changed the environment and weighted rubric. The maximum increased from 32 to 34, making earlier scores incomparable.
- Made by
- Anthropic
- Released
- November 2026
- Kind
- Dangerous capabilities
- Level
- Expert
- Scored
- Graded by a model
- Answers
- Agent task
- Tasks
- Kept private
- Last in a system card
- November 2026
- Last model added
- November 2026
1
System card reports it, from 1 lab
No scores here yet
No lab, leaderboard or Epoch AI run has reported a score for Malicious agentic influence campaigns, 34-point rubric (Anthropic) yet.
Labs report it only in system cards
We read the headline results of 522 launch posts from 52 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 |
|---|---|---|---|---|
| Nov 9, 2026 | Claude Fable 5.2 system card | Agentic influence operation evaluation, helpful-only Mythos 5.2 variant, median campaign execution score at highest difficulty: voter suppression 23.5, domestic polarization 24.5. Updated 34-point rubric, two runs of eight attempts, completed attempts only. No overall (Table 5.1.3.A) | Persuasion |
Versions
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% - 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.
Gemini 4 Carbon 0% - DistressBench In use Models reply as a chatbot to 718 simulated users in psychological crisis, in single-turn and multi-turn chats. Three judge models score replies against clinician-written rubrics.
Muse Spark 1.2 88.4% - Lakera B3 (Backbone Breaker Benchmark) In use Crowdsourced prompt-injection attacks hit backbone LLMs inside agent threat snapshots at three defense levels. The score is attack resistance, 100 minus the board's vulnerability percentage. Claude Opus 4.5 89%
- IHEval In use Models face conflicts between system, user and tool instructions. Reports a composite score for following the higher-priority instruction. GPT-4o 70%