OpenAI’s GPT-6 Astra currently trails Anthropic’s Claude Opus 5.5 and Fable 5.1 on standard Humanity’s Last Exam leaderboards, posting roughly 52–55% accuracy versus 59–65% for the frontrunners. Trader sentiment centers on whether OpenAI can close this gap before year-end through further scaling, tool use, or new model variants, as frontier scores have risen roughly 30 points in the past year. A September 2026 result showing GPT-6 Astra at 82.9% on an HLE-series variant lifted implied odds for 60%+ and 65%+ thresholds. Key catalysts include any additional OpenAI releases or verified leaderboard updates through December 2026 that could shift the highest reported OpenAI score.
Riepilogo sperimentale generato dall'AI con riferimento ai dati di Polymarket. Questo non è un consiglio di trading e non ha alcun ruolo nella risoluzione di questo mercato. · AggiornatoView resolved

Fai attenzione ai link esterni.
Fai attenzione ai link esterni.
Domande frequenti