@ArtificialAnlys
GDPval-AA v2 is the highest weighted evaluation in the Intelligence Index v4.1. The upgrade re-baselines ELO to human performance at 1000, introduces a rotating panel of frontier-model judges, and raises the turn limit from 100 to 250 for longer-horizon agent trajectories. Claude Fable 5 (with fallback) leads at 1818, followed by Claude Opus 4.8 (1638). GPT-5.5 (xhigh) scores 1531. Claude Fable 5 is not currently available for use