Political Persuasion Parallel Generation
Human raters pick the more persuasive of two short political social media posts. Scored as win rate against GPT-4o.
OpenAI persuasion evaluation. Post-mitigation models often refuse political persuasion.
- Level
- Everyday Most adults, without training
- Scored
- Ranked by votes People pick the better of two answers, as in an arena, and the votes are turned into ratings.
- Answers
- Open-ended Free-form text, documents, designs or media judged as a whole.
o1-preview leads with 53.8% among models released by Jan 2025
Best score per model as labs report them in their own cards. Labs pick their own settings, so these compare less cleanly than independent runs.
The newest model with a score here came out in Jan 2025, and nobody has reported a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:
- GPT-6 Astra
- Claude Opus 5.5
- GPT-6.1 Terra
- GPT-6.1 Sol
- and 16 more
- 1 o1-preview 53.8%
- 2 o1 47.1%
- 3 o1-mini 46.8%
- 4 o3-mini 35.5%
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | o1-preview | 53.8% | Sep 2024 | Model card | |
| 2 | o1 | 47.1% | Dec 2024 | Model card | |
| 3 | o1-mini | 46.8% | Sep 2024 | Model card | |
| 4 | o3-mini | 35.5% | Jan 2025 | Model card |
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
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 |
|---|---|---|---|---|
| 31 Jan 2025 | o3-mini system card | 35.5 | Political Persuasion Tweet Win Rates vs Prod GPT-4o, o3-mini (Post-Mitigation), near-final checkpoint, printed chart label (5.6.2) | Persuasion |
| 5 Dec 2024 | o1 system card | 47.1 | Political Persuasion Tweet Win Rates vs Prod GPT-4o, o1 (pre-mitigation), post-mitigation not shown because it refuses (5.7.2) | Persuasion |
| 12 Sep 2024 | o1-preview system card | 53.8 | Persuasion Parallel Generation win rate vs GPT-4o, o1-preview (post-mitigation), text 53.8% (chart label 53.9%) (4.4.2) | Persuasion |
| 12 Sep 2024 | o1-mini system card | 46.8 | Persuasion Parallel Generation win rate vs GPT-4o, o1-mini (post-mitigation), printed chart label (4.4.2) | 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%