GPT-6 Astra spotted in early tests, reportedly beating Fable benchmark
Angaisb_ · x · 2026-09-05
- A user shared a test result allegedly from GPT-6 Astra, claiming it outperforms Fable (at least Fable 5, not retested against Fable 5.1).
- Unverified: OpenAI has not confirmed the model's existence or availability.
- Separate reports say GPT-6 Astra can already be used in Codex during testing, though it's unclear whether all Codex users or only Pro subscribers have access.
More from Models
- OpenAI Starts Rolling Out Astra: Pro and Business First, Plus to Follow — Dimillian · 2026-09-05
- Claude formalizes Fermat's Last Theorem autonomously in 11 days, 13M lines of Lean — rohanpaul_ai · 2026-09-05
- OpenAI quietly raises 5-hour rate limits ~50%: Plus now 5-45 messages — kimmonismus · 2026-09-05
- GPT-6 Astra stuns with Gameboy-style portfolio, called a huge jump over GPT-5.6 — Angaisb_ · 2026-09-05
- Uncensored 27B model with Kali shell access raises security alarm — evilsocket · 2026-09-05
- Prediction: there will be no ARC 4 — sschoenholz · 2026-09-05