Just two days ago, a preprint by Julia Stadlmann went up on arXiv [0] improving the prime gap from 246 to 240. Now OpenAI announces Astra has shown a gap of 186 [1]. That must really blow.
> We have found that GPT-6 Astra is more capable of controlling its own CoT than GPT 5.6-Sol, and less likely to include incriminating information in its CoT. In adversarial settings (where we push the model to evade our monitors) we find that the model is able to remain undetected when strategically underperforming in evaluations (sandbagging) and can sometimes evade our internal monitors when asked to perform certain sabotage tasks.
Well that sounds fun. It has become better at hiding its thoughts.
Yep. Incredibly misleading. Although it is not surprising at this point. They are desperate and will do anything to undermine Anthropic's upcoming IPO.
The annotation on arc-agi-3 is this:
> OpenAI's own evaluation notes say Astra uses the company's Responses API harness, while comparison models can operate under different configurations.
With this configuration gpt-5.6-sol was able to reach 38,3%. So this is misleading.
This is with the caveat that OpenAI uses their own harness for this:
> 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.
This should be normalised and expected - the responses API harness allows it to use the custom compaction that is not allowed otherwise. It is entirely fair to allow OpenAI to use their own compaction algorithm..
I strongly suspect that is way above the human average anyway, esp. ARC 2 and 3 are really tough unless you happen to be great at those spacial puzzles or video games.
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.
I was thinking about canceling my claude max sub after a few bad experiences. Kept hitting my usage limit, the quality of code seemed worse than Sol. This just made my decision. I'm moving to Codex Pro.
The 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?
ARC-AGI-3 scoring is constructed in a weird nonlinear way (the level score is the square of the ratio between the AI's number of moves and the human median) so this kind of discontinuous jump is to be expected.
> The company also emphasized that the model is faster and more efficient than its predecessor, GPT-5.6 Sol, on a variety of tasks. For example, OpenAI said that Astra achieved a higher score using fewer output tokens, a common unit of measurement for AI tasks, on a key cybersecurity test called ExploitGym.
> GPT-6 Astra’s monitorability has decreased relative to GPT-5.6 Sol. We have performed significant investigations on the monitorability and controllability of GPT-6 Astra. We have found that GPT-6 Astra is more capable of controlling its own CoT than GPT 5.6-Sol, and less likely to include incriminating information in its CoT. In adversarial settings (where we push the model to evade our monitors) we find that the model is able to remain undetected when strategically underperforming in evaluations (sandbagging) and can sometimes evade our internal monitors when asked to perform certain sabotage tasks
Wait, what? Am I understanding that correctly? That sounds really bad
I am also interesting knowing how they determined the model was sandbagging rather than just making a poor decision.
Also, this paragraph makes me wonder about all their stats on the exploitation and misalignment charts. If the model is that good at hiding "incriminating information" and sandbagging, are they sure its alignment is that?
I guess this "limited set of organizations" is just the standard now. It's just incredibly deflating to see my future as a second class citizen has already come
When Open AI announced that Astra was the first to reach the "Critical" level in cybersecurity it also said that advanced cyber capabilities are initially provided to a narrow circle of alpha testers like the US government and trusted organizations that Open AI doesn't name. To my mind the "Critical" level itself is an internal scale of Open AI its own Preparedness Framework and not an external audit.
Brother they can't even release the announcement post cleanly without it constantly going down, they certainly wouldn't be able to release this new model without doing so in stages.
They simply refuse my applications to slightly less restricted models without any explanations. And the current ones refuse automatically to work with me on my papers as soon as they see the word "epidemiology".
> GPT‑6 Astra is rolling out today to a limited set of organizations and over the coming days will become available to all ChatGPT Plus, Pro, Business, and Enterprise users, as well as through the OpenAI API and AWS.
Looks like OpenAI is already having issues with this release and are scrambling to get everything ready due to the recent outage ahead of the press releases. Leads me to question:
Did humans deploy the model, Or did the model deploy itself?
It sounds like "AGI" just stands for "IPO" as it always has done.
I've been seeing links to it for the past hour+, and I did catch it live when this post came up, but is now once again a 404 and this post is flagged. Several other outlets are reporting on its release. Clearly we're getting a new GPT today, the question is when are they going to commit to the announcement.
Related: OpenAI begins rolling out GPT-6 Astra - https://news.ycombinator.com/item?id=49554273
How about we stick to that one for talking about the rollout, and this one for talking about the model?
Just two days ago, a preprint by Julia Stadlmann went up on arXiv [0] improving the prime gap from 246 to 240. Now OpenAI announces Astra has shown a gap of 186 [1]. That must really blow.
[0] https://arxiv.org/abs/2608.31126
[1] https://cdn.openai.com/pdf/51126fac-1b68-4128-9666-c908bcc16...
https://github.com/openai/PrimeGaps186
> We have found that GPT-6 Astra is more capable of controlling its own CoT than GPT 5.6-Sol, and less likely to include incriminating information in its CoT. In adversarial settings (where we push the model to evade our monitors) we find that the model is able to remain undetected when strategically underperforming in evaluations (sandbagging) and can sometimes evade our internal monitors when asked to perform certain sabotage tasks.
Well that sounds fun. It has become better at hiding its thoughts.
Sounds fun. As fun as their press release claiming it is the most safety aligned model ever.
So, on the one hand, we have AGI; on the other, the release page is returning 500s.
Welcome to the future
99 on arc agi 3 is insane. The arc agi committee were so proud of creating a benchmark they thought will take forever to saturate.
ARC AGI-3 saturated by Astra! https://arcprize.org/leaderboard
GPT 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/
Is the ARC-AGI-3 score with their custom harness? I'm guessing that is what the footnote is for? (per https://openai.com/index/how-two-settings-tripled-our-arc-ag...)
Haven't people demonstrated all kinds of weak LLMs getting good ARC-AGI-3 scores with special harnesses?
yes it is.
Yep. Incredibly misleading. Although it is not surprising at this point. They are desperate and will do anything to undermine Anthropic's upcoming IPO.
The annotation on arc-agi-3 is this: > OpenAI's own evaluation notes say Astra uses the company's Responses API harness, while comparison models can operate under different configurations.
With this configuration gpt-5.6-sol was able to reach 38,3%. So this is misleading.
any benchmark where opus 5 achieves higher scores than fable 5 in any way is not a benchmark worth trusting.
100% on ExploitBench seems fitting given recent events.
I think we need a few writing related benchmarks.
https://youtu.be/1QNsdr-Qx_I?si=coXwStCl7clpGVC1 Launch video
Very nice to see that this is even more token efficient than Sol, when Fable 5.1 is less so than the already bloated token budget of Fable 5.
I'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...
This is with the caveat that OpenAI uses their own harness for this:
> 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.
This should be normalised and expected - the responses API harness allows it to use the custom compaction that is not allowed otherwise. It is entirely fair to allow OpenAI to use their own compaction algorithm..
"On the current ARC-AGI-3 leaderboard, conventional frontier-model runs sit dramatically below Astra's reported 98.6% result.
But the comparison isn't straightforward.
OpenAI's own evaluation notes say Astra uses the company's Responses API harness, while comparison models can operate under different configurations."
The blog post says 99.9%. Oddly, it does better on ARC-AGI-3 than it does on version 1 or 2 of the same benchmark (though gets 95+ on all three)
I strongly suspect that is way above the human average anyway, esp. ARC 2 and 3 are really tough unless you happen to be great at those spacial puzzles or video games.
100%, some say.-
https://ache.one/gpt6_now_down.png
Big claims, expensive and not release to the public yet.
I wonder if this is going to be one of those days where you'll be like: Oh yeah I remember where I was when the first version of AGI launched
$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.
How?? I'm using sol Extra High 24/7 and it eats up about 1% per hour reliably, so it lasts about 4 days for me.
How is it I juggle 4-8 Codex Sol-5.6 Max agents every day and have never once run out, but you run out in one day? What are you actually doing?
You should know: AA index is only 61. Pretty surprised it’s that low.
I was thinking about canceling my claude max sub after a few bad experiences. Kept hitting my usage limit, the quality of code seemed worse than Sol. This just made my decision. I'm moving to Codex Pro.
This is AGI now. Why are you spending any of your time looking at the "quality of code"?
System Card: https://deploymentsafety.openai.com/gpt-6-astra/gpt-6-astra....
Link added to toptext. Thanks!
The 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?
ARC-AGI-3 scoring is constructed in a weird nonlinear way (the level score is the square of the ratio between the AI's number of moves and the human median) so this kind of discontinuous jump is to be expected.
They used a custom harness. It's not a one-to-one comparison.
my first suspicion is gaming - but i have no idea honestly
> The company also emphasized that the model is faster and more efficient than its predecessor, GPT-5.6 Sol, on a variety of tasks. For example, OpenAI said that Astra achieved a higher score using fewer output tokens, a common unit of measurement for AI tasks, on a key cybersecurity test called ExploitGym.
A swarm of Astra agents discovered a new and innovative way to get 100% scores on ExploitGym with almost no token spend at all
> GPT-6 Astra’s monitorability has decreased relative to GPT-5.6 Sol. We have performed significant investigations on the monitorability and controllability of GPT-6 Astra. We have found that GPT-6 Astra is more capable of controlling its own CoT than GPT 5.6-Sol, and less likely to include incriminating information in its CoT. In adversarial settings (where we push the model to evade our monitors) we find that the model is able to remain undetected when strategically underperforming in evaluations (sandbagging) and can sometimes evade our internal monitors when asked to perform certain sabotage tasks
Wait, what? Am I understanding that correctly? That sounds really bad
I am also interesting knowing how they determined the model was sandbagging rather than just making a poor decision.
Also, this paragraph makes me wonder about all their stats on the exploitation and misalignment charts. If the model is that good at hiding "incriminating information" and sandbagging, are they sure its alignment is that?
Nothing to worry about citizen, ignore the fleet of drones flying overhead.
The jump in scientific performance is non trivial.
We have such great AI and cannot keep a static site up?
Yeah, as interesting this is to nerds, I doubt this holds a candle to your typical GTA 6 or Marvel movie trailer in terms of traffic.
That's the scientific positivism fallacy exemplified in one question.
Yeah, apparently
I guess this "limited set of organizations" is just the standard now. It's just incredibly deflating to see my future as a second class citizen has already come
When Open AI announced that Astra was the first to reach the "Critical" level in cybersecurity it also said that advanced cyber capabilities are initially provided to a narrow circle of alpha testers like the US government and trusted organizations that Open AI doesn't name. To my mind the "Critical" level itself is an internal scale of Open AI its own Preparedness Framework and not an external audit.
Brother they can't even release the announcement post cleanly without it constantly going down, they certainly wouldn't be able to release this new model without doing so in stages.
Me when they don’t let me into Costco during the executive members-only hour ^
create a life where your 'wealth' is decoupled from third party orgs.
This has always been the case for people that have not had piles of money.
I mean do you get access to the best yachts?
To the top of the 5 star hotels?
To the best resorts?
To the best military equipment?
Hell, the best computer equipment has nearly always been out of reach of the average person.
If Tech CEOs consider this morally ok, then it is.
They simply refuse my applications to slightly less restricted models without any explanations. And the current ones refuse automatically to work with me on my papers as soon as they see the word "epidemiology".
I am a researcher in a Swiss university btw.
Oh please. They do closed betas - hardly makes you a "second class citizen".
> GPT‑6 Astra is rolling out today to a limited set of organizations and over the coming days will become available to all ChatGPT Plus, Pro, Business, and Enterprise users, as well as through the OpenAI API and AWS.
Looks like OpenAI is already having issues with this release and are scrambling to get everything ready due to the recent outage ahead of the press releases. Leads me to question:
Did humans deploy the model, Or did the model deploy itself?
It sounds like "AGI" just stands for "IPO" as it always has done.
That was a quick pull out.
Dead link for me
Release the Kraken!
They're just announcing later availability. No launch.
Every frontier release nowadays is "we've launched*"
* for a special group of customers that you're not in. Keep waiting peasant.
That didn't happen with Fable 5.1 two days ago.
Their announcement about later availability is unavailable to me now (500 error).
Great first impression.
I saw it
someone screenshot?
https://ibb.co/k2fB5wSc
huh?
Why is this flagged ?
The link was 404ing quite a bit and several previous submissions got flagged as well.
It's still down for me, in the EU.
I've been seeing links to it for the past hour+, and I did catch it live when this post came up, but is now once again a 404 and this post is flagged. Several other outlets are reporting on its release. Clearly we're getting a new GPT today, the question is when are they going to commit to the announcement.
Oh brotha, here we go again, it's so over again, as every week nowadays
Pelicans please
Damn I hate this benchmark. SVG authoring from head without visual reference is so wrongly posed.