Manifold MarketsSem KYCDados de resolução verificadosRazoavelmente calibradoPrevisão da comunidade atualNão 63.5%
Previsores
8
Tipo de pergunta
binary
Metodologia
Play-money forecasting platform
Tipo de fonte
Previsão
Dados do mercado
Atualizado há 12 minutos
10/02/25, 01:00 UTC1/01/28, 04:59 UTC
Tendências
Mercados Relacionados
Perguntas relacionadas para dar contexto, não uma comparação de contratos equivalentes.
Will Al achieve 85% or higher on the Humanity's Last Exam benchmark before 2028?
Manifold MarketsWill Al achieve 85% or higher on the Humanity's Last Exam benchmark before 2030?
Manifold MarketsWill Al achieve 85% or higher on the Humanity's Last Exam benchmark before 2027?
Manifold MarketsWill Al achieve 95% or higher on the Humanity's Last Exam benchmark before 2027?
Manifold MarketsHighest score on Humanity's Last Exam before Dec 31, 2027?
KalshiHighest Kimi score on Humanity’s Last Exam in 2026?
PolymarketRegras
Humanity's Last Exam (HLE) is a benchmark designed to evaluate Al systems' reasoning and problem-solving capabilities across a wide range of academic disciplines, including mathematics, humanities, and natural sciences.
- Developed collaboratively by the Center for Al Safety and Scale Al, HLE comprises 3,000 unambiguous and verifiable academic questions contributed by nearly 1,000 subject-matter experts from over 500 institutions across 50 countries.
- The dataset is multimodal, with approximately 10% of the questions requiring both image and text comprehension, while the remaining 90% are text-based.
- As of early 2025, state-of-the-art Al models have demonstrated limited success on the HLE benchmark.
- For instance, OpenAl's 03-mini (high) model achieved an accuracy of 13% when evaluated solely on text-based questions.
- OpenAl's Deep Research agent, which leverages the 03 model for extensive web browsing and data analysis, reached an accuracy of 26.6% on the HLE benchmark.