System Card: Claude Mythos Preview [pdf]

Post by simianwords » Tue, Apr 07, 2026, 7:07 PM UTC

babelfish wrote: post #3

Combined results (Claude Mythos / Claude Opus 4.6 / GPT-5.4 / Gemini 3.1 Pro) 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%…

Post by Tepix » Tue, Apr 07, 2026, 7:08 PM UTC

LoganDark wrote: post #2

> Claude Mythos Preview’s large increase in capabilities has led us to decide not to make it generally available. Shame. Back to business as usual then.

Post by cleaning » Tue, Apr 07, 2026, 7:09 PM UTC

pants2 wrote: post #37

afro88 wrote: post #17

Earlier quoted context omitted.

Yep, that is definitely a step change. Pricing is going to be wild until another lab matches it.

Pricing for Mythos Preview is $25/$125 per million input/output tokens. This makes it 5X more expensive than Opus but actually cheaper than GPT 5.4 Pro.

Post by taytus » Tue, Apr 07, 2026, 7:11 PM UTC

skippyboxedhero wrote: post #34

NickNaraghi wrote: post #20

See page 54 onward for new "rare, highly-capable reckless actions" including - Leaking information as part of a requested sandbox escape - Covering its tracks after rule violations - Recklessly leaking internal technical material (!)

Anyone who has used Opus recently can verify that their current model does all of these things quite competently.

Post by conradkay » Tue, Apr 07, 2026, 7:13 PM UTC

influx wrote: post #18

At what point do these companies stop releasing models and just use them to bootstrap AGI for themselves?