Every's hands-on: GPT-6 ASTRA is the best writing model yet, with wild computer-use that runs for hours
every · x · 2026-09-04
Every tested OpenAI's newly released GPT-6 ASTRA across coding, writing, and knowledge work. Verdict: a big upgrade over 5.6-Sol, though nagging habits keep it below Fable at the top end.
- Writing: the best writing model the author has tried — fast, minimal slop, easy to steer; it one-shotted the first draft of its own review.
- Computer use: can operate complex apps for hours at a time, including a first cut of the Fable 5.1 review video.
- Overall strong across the board, with some frustrating quirks.
More from Models
- Perplexity's WANDR Eval: GPT-6 Astra Tops at 0.682, $11.98 Per Task — cameronstow · 2026-09-04
- Blogger: Last Week May Mark the Closest Gap Between Open-Weight and Frontier Closed Models — toptickcrypto · 2026-09-04
- UK AISI's Clever New Eval Tests Rogue AI Behavior — and Astra Fails Badly — ShakeelHashim · 2026-09-04
- Arize argues MiniMax is underrated for agentic workloads for architectural reasons — aparnadhinak · 2026-09-04
- Gary Marcus asks: is Astra a pure LLM or an undisclosed neurosymbolic hybrid? — GaryMarcus · 2026-09-04
- GPT-6 Astra tops Mercor's APEX-Agents leaderboard at 62.4% on professional tasks — sherwinwu · 2026-09-04