GPT-6 Astra leaks in benchmark: 279/280 enterprise tasks done, zero hallucination

ryanshrout · x · 2026-09-06

Baxate quotes Signal65's preliminary test results for the rumored GPT-6 Astra (unverified, not officially confirmed):

The thread's core point: don't evaluate models by $/M tokens alone — "cost per task" or "intelligence per token" is what matters for enterprise deployments.

Related event: Leaked Benchmarks Claim GPT-6 Astra Aces Enterprise Tasks(2 posts)→

Original post →

More from Models

Models channel →