Home · Archive · Tech & AI · AI Models

Live marketTech & AI · AI Models

Will the highest score achieved by an Anthropic Claude model on Humanity’s Last Exam in 2026 be 65% or higher?

26%

crowd says YES

YES 26%

NO 74%

Closes: closes in 150d0 pts · 24hPolymarket

News · NPRHN 58 ptsNews · CBS NewsPolymarket $10k vol

News moving this market

Why did OpenAI's and Anthropic's AI models hack other companies? - NPR — NPR
CEO of AI firm Hugging Face calls last month's hack by OpenAI model "very weird and unprecedented" - CBS News — CBS News

View on Polymarket →

Discussion

Loading comments…