According to Moonshot AI, on general AI agent benchmarks, Claude Fable 5 continues to lead in overall reasoning. It scored 1,760 on GDPval-AA v2 Elo, ahead of GPT-5.6 Sol (1,748) and Kimi K3 (1,668). Fable 5 also topped the AA-Briefcase Elo benchmark with 1,583, while Kimi K3 followed at 1,548.
