GPT-6 Astra beats Fable 5.1 on Terminal science and Automation benchmarks

ChrisGPT · x · 2026-09-04

Blogger ChrisGPT shares GPT-6 Astra benchmark screenshots, claiming the new model "mogs" predecessor Fable 5.1 on Terminal science and Automation Bench. Scores are shown in an image from a third party — pending official confirmation and independent retests.

Related event: Leaked GPT-6 Astra benchmarks claim ARC-AGI-3 jump to 98.6%, unconfirmed by OpenAI(13 posts)→

Original post →

More from Models

Models channel →