{"slug": "appendix-b-additional-tables", "title": "Appendix B: Additional tables", "summary": "A Pew Research Center analysis found that OpenAI's GPT-5.1 and Anthropic's Claude Opus 4.6 each matched real American Trends Panel survey data within 5.0 percentage points on only a subset of questions, with GPT-5.1 accurate on 9 questions, Claude Opus 4.6 on 13, and both models on 1, according to the study's appendix tables. The synthetic \"digital twins\" were run with low reasoning, extended profile information and expert reflection, and the underlying survey of U.S. adults was conducted Jan. 20-26, 2026, with replications March 2-3 (GPT-5.1) and March 9-12 and April 7-10 (Claude Opus 4.6). Pew titled the accompanying report \"Can AI Stand In for Human Survey-Takers? Not Really.", "body_md": "Different models get different questions correct\n\n*Questions where each synthetic sample achieved a question-level average absolute error of 5.0 percentage points or less, when compared with real ATP data*\n\n| GPT-5.1 | Both models | Claude Opus 4.6 | \n|---|---|---|\n| • Whether there are clear solutions to most big issues facing the country today | • Have an IRA, 401(k) or similar retirement account | • Satisfaction with the way things are going in this country today | \n| • Whether 2026 will be better than or worse than 2025 |  | • Whether voting gives people like you some say about how government runs things | \n| • Preference for living in a community where houses are larger and farther apart or smaller and closer to each other |  | • Whether your side has been winning more often than losing in political issues that matter to you over the last few years | \n| • Concern about the cost of housing |  | • Whether the Trump administration’s tariff policies will have a positive or negative overall effect on the country | \n| • Participation in a political campaign, meeting, protest or rally in the last two years |  | • Favorability of suspending all asylum applications from people seeking to live in the U.S. to escape violence or danger | \n| • Whether it’s acceptable or not for federal immigration officers to wear face coverings that hide their identities while working |  | • Whether it matters or not which party wins control of Congress in the 2026 elections | \n| • Trump presidential approval |  | • Whether Trump will be a successful or unsuccessful president in the long run | \n| • Ease or difficulty of someone obtaining an abortion in the area where you live |  | • Whether Democratic congressional leaders this year should work with Trump to accomplish things or stand up to Trump on issues important to their voters | \n| • Whether police should be allowed to stop and search anyone who fits the general definition of a crime suspect |  | • Whether obtaining an abortion in the area where you live should be harder, easier or about the same as it is now” | \n|  |  | • Favor or oppose pausing visa applications from people in 75 countries seeking to legally immigrate to the U.S. | \n|  |  | • Whether Trump’s economic policies have made economic conditions better, worse or have had not much of an effect” | \n|  |  | • Whether you find talking about politics with people you disagree with interesting and informative or stressful and frustrating | \n|  |  | • Confidence that Trump has the leadership skills needed to be president | \n\nNote: \n\nSource: Survey of U.S. adults and “digital twins” synthetic analysis using models set to low reasoning with extended profile information and expert reflection. Survey was conducted Jan. 20-26, 2026 (replicated March 2-3 with OpenAI GPT-5.1; and replicated March 9-12 and April 7-10 with Claude Opus 4.6).\n\n[Refer to the Wave 185 questionnaire](https://www.pewresearch.org/wp-content/uploads/sites/20/2026/01/PP_2026-01-29_views-of-trump_questionnaire.pdf)for full question wording.\nSource: Survey of U.S. adults and “digital twins” synthetic analysis using models set to low reasoning with extended profile information and expert reflection. Survey was conducted Jan. 20-26, 2026 (replicated March 2-3 with OpenAI GPT-5.1; and replicated March 9-12 and April 7-10 with Claude Opus 4.6).\n\n“Can AI Stand In for Human Survey-Takers? Not Really”\n\nPEW RESEARCH CENTER\n\nDifferent models get different questions correct\n\n*Questions where each synthetic sample achieved a question-level average absolute error of 5.0 percentage points or less, when compared with real ATP data*\n\n| Independent variable | n1 | n2 | \n|---|---|---|\n| Germany | 40 | 60 | \n| Spain | 50 | 50 | \n| France | 60 | 40 | \n\nNote: \n\nSource: Survey of U.S. adults and “digital twins” synthetic analysis using models set to low reasoning with extended profile information and expert reflection. Survey was conducted Jan. 20-26, 2026 (replicated March 2-3 with OpenAI GPT-5.1; and replicated March 9-12 and April 7-10 with Claude Opus 4.6).\n\n[Refer to the Wave 185 questionnaire](https://www.pewresearch.org/wp-content/uploads/sites/20/2026/01/PP_2026-01-29_views-of-trump_questionnaire.pdf)for full question wording.\nSource: Survey of U.S. adults and “digital twins” synthetic analysis using models set to low reasoning with extended profile information and expert reflection. Survey was conducted Jan. 20-26, 2026 (replicated March 2-3 with OpenAI GPT-5.1; and replicated March 9-12 and April 7-10 with Claude Opus 4.6).\n\n“Can AI Stand In for Human Survey-Takers? Not Really”\n\nPEW RESEARCH CENTER", "url": "https://wpnews.pro/news/appendix-b-additional-tables", "canonical_source": "https://www.pewresearch.org/data-labs/2026/09/30/appendix-b-additional-tables-6/", "published_at": "2026-09-30 17:55:24+00:00", "updated_at": "2026-09-30 18:19:39.687665+00:00", "lang": "en", "topics": ["artificial-intelligence", "large-language-models", "ai-research", "ai-safety"], "entities": ["Pew Research Center", "GPT-5.1", "OpenAI", "Claude Opus 4.6", "Anthropic", "American Trends Panel"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/appendix-b-additional-tables", "markdown": "https://wpnews.pro/news/appendix-b-additional-tables.md", "text": "https://wpnews.pro/news/appendix-b-additional-tables.txt", "jsonld": "https://wpnews.pro/news/appendix-b-additional-tables.jsonld"}}