Loading page…
Preferred languages
More languages supported by Google Translate
Open the selector to load the current language catalog.
Translations are provided by Google Translate.
Loading page…
Preferred languages
More languages supported by Google Translate
Open the selector to load the current language catalog.
Translations are provided by Google Translate.
Knowledge benchmark
Humanity's Last Exam Diamond with web and code tools. Every model the catalog carries a published HLE-Diamond (web+code) value for, ranked by that value.
Accuracy on HLE-Diamond with constrained web search, page fetching, and code execution at high reasoning effort.
The benchmark is defined by Introducing HLE-Diamond, but the catalog carries no value for it yet. An absent value is shown as absent here rather than as a zero.
What the benchmark measures and how its value is published, from the source’s own record.
HLE-Diamond (web+code) (Humanity's Last Exam Diamond with web and code tools) is a knowledge benchmark published by Introducing HLE-Diamond. Accuracy on HLE-Diamond with constrained web search, page fetching, and code execution at high reasoning effort. Its evaluation set is described by the source as 1,000 expert questions with web and code tools. The source rates its difficulty as frontier expert knowledge and reasoning.
Each model's result is published by Introducing HLE-Diamond as accuracy with web and code, reasoning high. ModelScale prints that value to 1 decimal place, exactly as published, and never converts or rescales it. This page ranks the 0 models that carry a published value, highest value first; a model the source never scored is left out rather than ranked at zero. The source does not state whether a higher value is the better result, so neither does this page.