GPT-6 Astra reportedly smashes automation bench record at 41.4%, up from 31.4%
sandersted · x · 2026-09-04
Developer @bryanhelmig shares two early observations on GPT-6 Astra:
- Benchmarks: it scores a record-shattering 41.4% on his automation bench, crushing the previous record of 31.4% held by fable 5.1 — a 10-point leap;
- Writing: the model's personality doesn't feel fried; its output is coherent and non-performative, noticeably more pleasant to read.
The thread is marked "1/?", suggesting more to come. Early-access anecdote, unverified, not official numbers.
More from Models
- Neuralese explained: why OpenAI's Astra architecture has safety researchers alarmed — ShakeelHashim · 2026-09-04
- K2 Horizon launches six fully open models from 0.9B to 375B with training code, data recipes and logs — aliscodes · 2026-09-04
- Is Astra AGI? Five contradictory answers that are all true at once — shaunralston · 2026-09-04
- Early Access Tester: GPT-6 Astra Built a Blender Werewolf in 8 Minutes and a World Simulator in 17 — TheMoonMidas · 2026-09-04
- swyx Burned 20B Tokens Stress-Testing Astra on Real AI Engineering Tasks — All for Under $6/Hour — charliermarsh · 2026-09-04
- OpenAI's Lukasz Kaiser: even we can't pinpoint what caused the Christmas coding-agent jump — a_karvonen · 2026-09-04