Matthew Berman Puts GPT-6 Astra Through Its Paces: Benchmarks, Demos and Browser Use
Matthew Berman · youtube · 2026-09-04
AI reviewer Matthew Berman published a full hands-on review of GPT-6 Astra (13 min), covering:
- Benchmark results and takeaways from the official blog
- A series of generative demos: Little Planet, Ratstronaut, 7 Islands, ASCII City, Sim City and more
- Browser-use testing in practice
- Closing critiques of the model
One of the first third-party reviews with a critical angle, plus a written review linked alongside.
Related event: Matthew Berman's Hands-On: GPT-6 Astra Is the Best Model He's Used(7 posts)→
More from Models
- Codex Down for Much of Rollout Day — and Users Not Getting New Model Either — RexDouglass · 2026-09-04
- 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