Manifold MarketsGeen KYCGeverifieerde afwikkelingsgegevensRedelijk gekalibreerdHuidige gemeenschapsvoorspellingNee 63.5%
Voorspellers
8
Vraagtype
binary
Methodologie
Play-money forecasting platform
Brontype
Voorspelling
Marktdata
Bijgewerkt 11 uur geleden
Verouderd10 feb 25, 01:00 UTC1 jan 28, 04:59 UTC
Trends
Gerelateerde Markten
Gerelateerde vragen voor context, geen vergelijking van gelijkwaardige contracten.
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 2027?
Manifold MarketsWill Al achieve 85% or higher on the Humanity's Last Exam benchmark before 2030?
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 score on Humanity’s Last Exam in 2026?
PolymarketRegels
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.