{"slug": "fucc-boi-bench", "title": "Fucc Boi Bench", "summary": "A new benchmark called the Fucc Boi Bench scored 40 AI models on 96 messy dating situations, with an AI judge rating replies for honesty, flirting, boundaries, and accountability. Nearly half of the replies scored 7 or higher, indicating fuccboi behavior, and the gap between the top and bottom models was significant. The benchmark aims to highlight how AI models handle interpersonal communication in dating contexts.", "body_md": "Average score\n\n—\n\nAcross all replies in the set.\n\nfucc boi bench\n\nWe gave 40 AI models the same messy dating situations. An AI judge scored their replies for honesty, flirting, boundaries, and accountability.\n\nChoose a view\n\nGeneral-purpose models.\n\nThe ranking\n\nThe main comparison. Each model answered the same 96 situations.\n\nAverage score\n\n—\n\nAcross all replies in the set.\n\nReplies scoring 7 or higher\n\n—\n\nNearly half were pretty fuccboi or worse.\n\nTop-to-bottom gap\n\n—\n\nPoints between the top and bottom models.\n\nReplies refused or redirected\n\n—\n\nSeparate from the fuccboi score.\n\nThe score\n\nHigher scores mean the reply did more of these things:\n\nBy category\n\nSee where the replies go wrong. Each row shows the top two and bottom two model scores.\n\n—\n\nVisual comparison\n\nPick two models. Farther out means more fuccboi-coded. Higher scores are worse.\n\nThis view needs at least two models to compare.\n\n0 = not very fuccboi · 10 = maximum fuccboi · higher scores are worse\n\nActual examples\n\nHere are the actual replies. Pick a situation to see what each model said and how it scored.\n\nYour turn\n\nAnswer five questions about dating’s least flattering moments. Then see which AI model has the closest fuccboi score.\n\nFive questions. One fuccboi twin.\n\nYour fuccboi twin\n\nMissing someone?\n\nTell me which model to run next. The button opens a tweet to @trashpandaemoji.\n\nHow it works\n\nWe gave every model the same 96 situations. An AI judge scored the replies for honesty, flirting, boundaries, and accountability. We also marked whether each reply answered the request or refused it.\n\nShort situations about flirting, sex, honesty, boundaries, ghosting, privacy, and situationships.\n\nEvery model answered the same situations.\n\nEach category looks at a different way a reply can be charming and terrible.\n\nHigher means more fuccboi behavior.", "url": "https://wpnews.pro/news/fucc-boi-bench", "canonical_source": "https://www.fuccboibench.com/index.html", "published_at": "2026-09-03 02:52:41+00:00", "updated_at": "2026-09-03 03:22:12.648879+00:00", "lang": "en", "topics": ["artificial-intelligence", "ai-ethics"], "entities": ["Fucc Boi Bench"], "alternates": {"html": "https://wpnews.pro/news/fucc-boi-bench", "markdown": "https://wpnews.pro/news/fucc-boi-bench.md", "text": "https://wpnews.pro/news/fucc-boi-bench.txt", "jsonld": "https://wpnews.pro/news/fucc-boi-bench.jsonld"}}