GPT-6 Astra
31–40 of 1001 posts
Re: GPT-6 Astra
#32The ARCC-AGI-3 performance is absolutely incredible. The magnitude of change here is so high that I'm almost incredulous. Is this real? Did the benchmark get gamed?
Re: GPT-6 Astra
#33GPT 6 Astra benchmarks https://cdn.thenewstack.io/media/2026/09/358eb84a-screenshot... Performance is significantly higher than Fable 5.1 Source: https://thenewstack.io/openai-gpt6-astra-benchmarks/
Re: GPT-6 Astra
#34I'm seeing reporting it gets 98.6% on ARC-AGI3[1] (previously like 30% with Fable) https://venturebeat.com/technology/welcome-to-the-agi-era-op...
> On ARC-AGI-3, GPT-6 Astra was run with our responses API harness , which changes two settings to better match real-world performance. The changes do not specifically target ARC-AGI-3.
Re: GPT-6 Astra
#35Re: GPT-6 Astra
#36$10 per million input tokens and $50 per million output tokens sol is $4 / $20
2.5x more expensive than Sol. Can expect 2.5x more usage in Codex subscription. Sol is already brutal (even after their recent fixes, it's just a token-hungry model: I go through a full 20x account per day, on Sol Med/High standard speed, with ~2 threads). I hope the efficiency gains are true, since their token efficiency claims for Sol were bullshit.
Re: GPT-6 Astra
#37Why is this flagged ?
Re: GPT-6 Astra
#38Re: GPT-6 Astra
#39They're just announcing later availability. No launch.
* for a special group of customers that you're not in. Keep waiting peasant.
Re: GPT-6 Astra
#40Big claims, expensive and not release to the public yet.