Why does GPT-6 Astra get mogged on the AA index? Caballero asks

ethanCaballero · x · 2026-09-04

Researcher Ethan Caballero questions GPT-6 Astra's weak showing on the Artificial Analysis index, a counterpoint to claims that it beats Fable 5.1 across nearly all benchmarks — suggesting results may vary depending on the evaluation source.

Related event: Community Questions GPT-6 Astra's Performance on Artificial Analysis Leaderboards(6 posts)→

Original post →

More from Models

Models channel →