X
Publisher · verified by editors
X: @ArtificialAnlys
AI news source. Articles are auto-selected and adapted by Hamidun News editors.
Latest publications

ResearchX: @ArtificialAnlys
Artificial Analysis releases AA-Omniscience v1.1: Net Score drops by about 2 points on average
In the updated AA-Omniscience v1.1 benchmark, models' Net Score is about 2 points lower on average, and the Spearman rank correlation with v1 is 0.98.

BusinessX: @ArtificialAnlys
Claude Opus 5.5 scores 68% on HLE-Diamond, but each task costs 35 times more
Artificial Analysis tested reasoning modes: Opus 5.5 climbs from 42% to 68%, GPT-6 Astra from 45% to 64%, while the cost per task rises 35x and 11x.