gpt-6THREAD
GPT-6 Sol and Luna hallucinate less than predecessors at max effort, Artificial Analysis says
Artificial Analysis reports that both GPT-6 Sol and Luna hallucinate less than their predecessors at max effort.
Artificial Analysis
@ArtificialAnlysArchived 2026.09.23Originally posted 2026.09.23
THREAD
GPT-6 Sol and Luna both hallucinate less than their predecessors at max effort.

GPT-6 Sol (max) gains 2 points in the Artificial Analysis Coding Agent Index at half the Cost per Task of its predecessor, while GPT-6 Luna (max) regresses by 2 points.

Artificial Analysis @ArtificialAnlysOriginally posted 2026.09.23
x.com/artificialanlys/status/2102462968084758810Archived 2026.09.23 10:21