Before 2027, will OpenAI release a frontier model with a 5:1 or better abstention to hallucination ratio on SimpleQA?
IAOne-Off2mois
Manifold MarketsSans KYCDonnées de résolution vérifiéesAssez bien calibréAlerte qualité des donnéesDonnées source dégradées
Données au 26 oct. 2026, 03:24 UTC · politique pm-quality-4
Prévision communautaire actuelleOui 61.2%
Prévisionnistes
8
Type de question
binary
Méthodologie
Play-money forecasting platform
Type de source
Prévision
Données du marché
Mis à jour il y a 8 heures
Obsolète20 sept. 25, 22:10 UTC31 déc. 26, 23:59 UTC
Tendances
Marchés Associés
Questions liées pour le contexte, et non une comparaison de contrats équivalents.
Before 2027, will OpenAI release a Frontier Model trained according to their "Why LLMs hallucinate" paper?
Manifold MarketsWill Microsoft train and release a frontier model in 2026?
Manifold MarketsWill China restrict the open release of frontier AI models above a capability threshold by end of 2026?
Manifold MarketsBefore 2028, will any AI lab release a frontier model that performs O(n) sequence modeling?
Manifold MarketsWhen will OpenAI release a personal AI agent?
KalshiWhen will OpenAI release Astra 6.1?
KalshiRègles
SimpleQA is an obscure trivia benchmark OpenAI uses to evaluate hallucination rate.
- Resolves yes if a Frontier model released by OpenAI declines to answer SimpleQA questions at least 5 times as often as it incorrectly answers them.
- To resolve yes, the model must not have access to the internet or any database of facts.
- I will be largely looking towards OpenAI's evaluations to resolve this market but will accept 3rd party evals if OpenAI stops using SimpleQA.
- OpenAI's latest frontier model GPT-5-thinking has only a 1:8 ratio.
- However, OpenAI claimed in a recent paper that they have new insights into why LLMs hallucinate and how to prevent them.
