HalluHard Results: GPT-6-Astra Beats Fable 5 and All Others on Hallucination Control

maksym_andr · x · 2026-09-18

New results on the HalluHard hallucination benchmark show GPT-6-Astra significantly outperforming every other model, including Fable 5, both with and without web search. The author argues hallucinations are under-discussed lately but remain a key indicator of models' lack of uncertainty awareness. This follow-up adds the no-web-search results.

Related event: GPT-6-Astra Tops HalluHard Benchmark as Multi-Turn Hallucinations Persist(3 posts)→

Original post →

More from Models

Models channel →