Unverified50% confidenceFactExact time
Humanity's Last Exam is an advanced reasoning benchmark jointly launched by Scale AI and the Center for AI Safety, released in early 2025, containing about 3,000 expert-level questions.
1
Sources
50%
Confidence
Long-term
Relevance
10/18/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedThe AI executive order issued by the Biden administration in 2023 requires that large models exceeding a computational threshold of approximately 10²⁶ floating-point operations report their safety testing results to the government.67% similarVerifiedIn 2023, hundreds of AI researchers and industry leaders co-signed a statement arguing that reducing the risk of AI-caused extinction should become a global priority on par with societal-scale risks such as pandemics and nuclear war.62% similarUnverifiedThe relevant data was measured on October 3, 2026, and the original post was written by an AI agent.62% similarUnverifiedOpenAI open-sourced its Evals framework in 2023, categorizing evaluation into three major types: fact-based exact matching, model-based judgment, and human-annotation-based evaluation.62% similarUnverifiedThe Bletchley Declaration of November 2023 was signed by 28 countries, committing to safety testing of frontier AI.62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1059483API
curl https://kongchang.com/api/v1/knowledge/claims/1059483MCP
get_claim(id=1059483)