WHAT NEW IN X11.04 WED

AI collections from X · 22 collections · 67,905 posts

Back to No.001 GPT-6 Astra in Practice: Tests, Use Cases, and FeedbackUpdated 11 hours ago
gpt-6IMAGE

GPT-6 Astra hallucination rate comparison sparks debate

A benchmark chart shows hallucination rates of 15.1% for Argon, 44.8% for GPT-6 Astra, and 72.6% for Claude Fable 5.1, with the poster asking why no one is discussing this metric.

bidyut
@bidyut_ioArchived 29 days agoOriginally posted 2026.10.05
GPT-6 Astra hallucination rate comparison sparks debate
bidyut @bidyut_ioOriginally posted 2026.10.05
Open original on X

Wait… yes, we know 1M output tokens matters. But considering Gemini’s history with hallucinations, this might be the more important benchmark. Argon: 15.1% GPT-6 Astra: 44.8% Claude Fable 5.1: 72.6% Not context. Not tokens. Why isn’t everyone talking about this?

This post quotes another post: x.com/bidyut_io/status/2105501411291386143

x.com/bidyut_io/status/2107079726334714113Archived 2026.10.06 10:04
Open original on X