Artificial Analysis launches the Intelligence Index v5, with new coding and science benchmarks, built on private datasets; Claude Opus 5.5 (max) leads at 58 (@artificialanlys)

Artificial Analysis has launched its Intelligence Index v5, introducing new coding and science benchmarks. This latest version is predominantly built on private datasets, enhancing its relevance to real-world applications. Claude Opus 5.5 (max) currently leads the index with a score of 58, indicating its strong performance across the evaluated model capabilities. The update includes 2 new benchmarks and 3 upgrades to the composite measure.