Artificial Analysis Intelligence Index v5

Artificial Analysis released Intelligence Index v5, their largest update since January, which now bases 60% of evaluations on private datasets and introduces two new benchmarks (FrontierCode 2.0 and Terminal-Bench-Science) along with three upgraded benchmarks. Claude Opus 5.5 leads the rankings with a score of 58, followed by GPT-6 Astra at 57, while the gap between proprietary and open-weight models has widened to 12 points. The index also tracks cost efficiency, with leading models varying by more than 13x in cost per task.