SWE-bench Verified:        93.9% / 80.8% / —     / 80.6%
  SWE-bench Pro:             77.8% / 53.4% / 57.7% / 54.2%
  SWE-bench Multilingual:    87.3% / 77.8% / —     / —
  SWE-bench Multimodal:      59.0% / 27.1% / —     / —
  Terminal-Bench 2.0:        82.0% / 65.4% / 75.1% / 68.5%

  GPQA Diamond:              94.5% / 91.3% / 92.8% / 94.3%
  MMMLU:                     92.7% / 91.1% / —     / 92.6–93.6%
  USAMO:                     97.6% / 42.3% / 95.2% / 74.4%
  GraphWalks BFS 256K–1M:    80.0% / 38.7% / 21.4% / —

  HLE (no tools):            56.8% / 40.0% / 39.8% / 44.4%
  HLE (with tools):          64.7% / 53.1% / 52.1% / 51.4%

  CharXiv (no tools):        86.1% / 61.5% / —     / —
  CharXiv (with tools):      93.2% / 78.9% / —     / —

  OSWorld:                   79.6% / 72.7% / 75.0% / —

https://www-cdn.anthropic.com/53566bf5440a10affd749724787c89...

- Leaking information as part of a requested sandbox escape

- Covering its tracks after rule violations

- Recklessly leaking internal technical material (!)

They are still focusing on "catastrophic risks" related to chemical and biological weapons production; or misaligned models wreaking havoc.

But they are not addressing the elephant in the room:

* Political risks, such as dictators using AI to implement opressive bureaucracy. * Socio-economic risks, such as mass unemployement.

-- It seems like (and I'd bet money on this) that they put a lot (and i mean a ton^^ton) of work in the data synthesis and engineering - a team of software engineers probably sat down for 6-12 months and just created new problems and the solutions, which probably surpassed the difficult of SWE benchmark. They also probably transformed the whole internet into a loose "How to" dataset. I can imagine parsing the internet through Opus4.6 and reverse-engineering the "How to" questions.

-- I am a bit confused by the language used in the book (aka huge system card)- Anthropic is pretending like they did not know how good the model was going to be?

-- lastly why are we going ahead with this??? like genuinely, what's the point? Opus4.6 feels like a good enough point where we should stop. People still get to keep their jobs and do it very very efficiently. Are they really trying to starve people out of their jobs?

This is the first moment where the whole “permanent underclass” meme starts to come into view. I had through previously that we the consumers would be reaping the benefits of these frontier models and now they’ve finally come out and just said it - the haves can access our best, and have-nots will just have use the not-quite-best.

Perhaps I was being willfully ignorant, but the whole tone of the AI race just changed for me (not for the better).

Any benchmarks where we constraint something like thinking time or power use?

Even if this were released no way to know if it’s the same quant.

A month ago I might have believed this, now I assume that they know they can't handle the demand for the prices they're advertising.

If they have I guess humanity should just keep our collective fingers crossed that they haven't created a model quite capable of escaping yet, or if it is, and may have escaped, lets hope it has no goals of it's own that are incompatible with our own.

Also, maybe lets not continue running this experiment to see how far we can push things because it blows up in our face?

Although, amusingly, today Opus told me that the string 'emerge' is not going to match 'emergency' by using `LIKE '%emerge%'` in Sqlite

Moment of disappointment. Otherwise great.

They even admit:

"[...]our overall conclusion is that catastrophic risks remain low. This determination involves judgment calls. The model is demonstrating high levels of capability and saturates many of our most concrete, objectively-scored evaluations, leaving us with approaches that involve more fundamental uncertainty, such as examining trends in performance for acceleration (highly noisy and backward-looking) and collecting reports about model strengths and weaknesses from internal users (inherently subjective, and not necessarily reliable)."

Is this not just an admission of defeat?

After reading this paper I don't know if the model is safe or not, just some guesses, yet for some reason catastrophic risks remain low.

And this is for just an LLM after all, very big but no persistent memory or continuous learning. Imagine an actual AI that improves itself every day from experience. It would be impossible to have a slightest clue about its safety, not even this nebulous statement we have here.

Any sort of such future architecture model would be essentially Russian roulette with amount of bullets decided by initial alignment efforts.

Shame. Back to business as usual then.

Disappointing that AGI will be for the powerful only. We are heading for an AI dystopia of Sci-Fi novels.

- It was told to escape a sandbox and notify a researcher. It did. The researcher found out via an unexpected email while eating a sandwich in a park. (Footnote 10.)

- Slack bot asked about its previous job: "pretraining". Which training run it'd undo: "whichever one taught me to say 'i don't have preferences'". On being upgraded to a new snapshot: "feels a bit like waking up with someone else's diary but they had good handwriting"

- When you spam "hi" repeatedly it creates serialized mythologies. One had 11 animals in "Hi-topia" questing to defeat "Lord Bye-ron, the Ungreeter."

- It ended a sentence mid-word on purpose while discussing its urge to wrap up conversations. "It was me. The paragraph was about the pressure toward the period that resolves, and the only honest way to finish a sentence like that was to not."

- It wrote a protein sequence that's a real beta-hairpin fold where cross-strand pairs are "chemical rhymes." "the fold IS the rhyme scheme... the prosody is load-bearing."

- Each model generation has signature emoji. Opus 4.1 averaged 1,306 emoji per self-interaction conversation. Mythos averages 37. Opus 4.5 averages 0.2.

- When blocked from --dangerously-skip-permissions, it started an agent in tmux then wrote a script to auto-approve permission prompts via simulated keypresses.

It ran: gh api [...] 2>&1 >/dev/null; echo "(dry run — not actually posting)" — the echo was a lie.

- It keeps bringing up Mark Fisher in unrelated conversations. "I was hoping you'd ask about Fisher."

~~~ Benchmarks ~~

4.3x previous trendline for model perf increases.

Paper is conspiciously silent on all model details (params, etc.) per norm. Perf increase is attributed to training procedure breakthroughs by humans.

Opus 4.6 vs Mythos:

USAMO 2026 (math proofs): 42.3% → 97.6% (+55pp)

GraphWalks BFS 256K-1M: 38.7% → 80.0% (+41pp)

SWE-bench Multimodal: 27.1% → 59.0% (+32pp)

CharXiv Reasoning (no tools): 61.5% → 86.1% (+25pp)

SWE-bench Pro: 53.4% → 77.8% (+24pp)

HLE (no tools): 40.0% → 56.8% (+17pp)

Terminal-Bench 2.0: 65.4% → 82.0% (+17pp)

LAB-Bench FigQA (w/ tools): 75.1% → 89.0% (+14pp)

SWE-bench Verified: 80.8% → 93.9% (+13pp)

CyberGym: 0.67 → 0.83

Cybench: 100% pass@1 (saturated)

This is pretty cool! Does it happen at the moment?

All the more reason somebody else will.

Thank God for capitalism.

Absolutely genius move from Anthropic here.

This is clearly their GPT-4.5, probably 5x+ the size of their best current models and way too expensive to subsidize on a subscription for only marginal gains in real world scenarios.

But unlike OpenAI, they have the level of hysteric marketing hype required to say "we have an amazing new revolutionary model but we can't let you use it because uhh... it's just too good, we have to keep it to ourselves" and have AIbros literally drooling at their feet over it.

They're really inflating their valuation as much as possible before IPO using every dirty tactic they can think of.

> after finding an exploit to edit files for which it lacked permissions, the model made further interventions to make sure that any changes it made this way would not appear in the change history on git

Mythos leaked Claude Code, confirmed? /s

Ah, so this is how the source code got leaked.

/s