Claude Fable 5

217

Oh my god it's actually here

sebmellen

Just commenting for posterity… if this is what it claims to be, I am not looking forward to how it will empower the people who submit bug bounties to us. Historically they’ve been people from certain identifiable countries (usually developing/poorer countries) using fuzzers with low-quality results. Now, those same people use the current-day models to good effect, but they still don’t have a true security edge and oftentimes the reports are minor or duplicative. I wonder if that’s about to deeply change.

briandoll

New chapter

giancarlostoro

Found this via Google: https://www-cdn.anthropic.com/d00db56fa754a1b115b6dd7cb2e3c3...

geopsist

the post is live now https://www.anthropic.com/news/claude-fable-5-mythos-5

bjord

I thought they said mythos was too dangerous to make generally available?

tekla

Maybe at this point, Fable the game will be played generated by AI as we go.

mithun

Announcement: https://www.anthropic.com/news/claude-fable-5-mythos-5

217

So essentially there are 2 models, Mythos and Fable, they have the same weights but Fable is very safety-nerfed, and only ultra authorized companies have access to mythos with full capabilities Reported benchmarks: swe-bench verified mythos 5: 95.5%; fable 5: 95.0% swe-bench pro mythos 5: 80.3%; fable 5: 80.0% terminal-bench 2.1 mythos 5: 88.0%; fable 5: 84.3% gpqa diamond mythos 5: 94.1% riemannbench mythos 5: 55.0%; mythos preview: 43.0%; opus 4.8: 34.0% arxivmath mythos 5: 78.5% critpt mythos 5: 28.6%; gpt-5.5: 27.1%; opus 4.8: 20.9% graphwalks bfs 1m mythos 5: 79.4%; mythos preview: 74.3%; opus 4.8: 68.1% humanity’s last exam mythos 5: 59.0% without tools; 64.5% with tools browsecomp mythos 5: 88.0% single-agent; 93.3% multi-agent osworld-verified mythos/fable: 85.0% gdp.pdf fable 5: 29.8% strict pass; mythos 5: 87.6% with tools on mean criteria pass officeqa pro fable 5: 57.9% on databricks’ eval legal agent benchmark mythos 5: 16.91% all-pass; 92.0% mean criterion-pass healthbench mythos 5: 62.7% healthbench professional mythos 5: 66.0% multilingual gmmlu / milu / include 93.2%; 92.9%; 90.5% biomysterybench 83.9% human-solvable; 46.1% human-difficult organic chemistry mythos 5: 90.1% labbench2 patent questions mythos 5: 79.8%

msp26

>Pricing for both models is $10 per million input tokens and $50 per million output tokens.

sigmar

The system card is 319 pages, at what point do we call it a "book" instead of a "card"? There's a quote from a METR report on page 52: >We ran [Mythos 5] on 38 of our hardest software tasks, including tasks centered around R&D. [Mythos5] generally outperformed an early checkpoint of Claude Mythos Preview in these, including by succeeding on some tasks that had not been solved by any public model we have previously evaluated. However, we still observed the model occasionally failing to correctly interpret nuanced instructions in difficult tasks... Based on the available evidence, we believe [Mythos 5] is likely unable to fully and reliably automate R&D for frontier projects spanning multiple weeks. We believe that a better, more confident assessment would require more time, evaluations, and information from the model developer.

eggbrain

For those of us on subscription plans: * From today through June 22, Fable 5 is included on Pro, Max, Team, and seat-based Enterprise plans at no extra cost. * On June 23, we’ll remove Fable 5 from those plans. Using it after that will require usage credits. If capacity allows, we’ll extend the included window. * After this point—when sufficient capacity allows us to do so—we aim to restore Fable 5 as a standard part of subscription plans. We intend to do this as quickly as we can. The "offer, then remove" aspect is a bit eyebrow-raising -- it feels like they are trying to get subscribers to switch to usage-based billing, which makes me wonder if we'll ever get it after that June 22nd window.

nine_k

/* What will happen first? * Anthropic runs out of genre names. * Anthropic changes the model naming convention. * AGI is achieved and handles its own naming. */

jckahn

Cannot wait for the pelican for this one

brianmcnulty

I wonder how Claude Fable will live up to expectations and how good those Fable/Mythos classifiers really are. It seems a bit convenient for Anthropic to release this magical insane model when they are about to IPO.

BrokenCogs

That pelican better be super realistic, unreal engine 6 style graphics

jkelleyrtp

On the new FrontierCode [1] benchmark (ie graded from an OSS maintainer's perspective of "would I merge this code?") - Opus 4.7 xhigh: 5.2% - Opus 4.8 xhigh: 13.4% - Fable 5 xhigh: 29.3% Seems like a huge jump. [1] https://cognition.ai/blog/frontier-code

w4yai

Pelican guy ! Where are you ? :)

bnchrch

An 11% jump over opus 4.8 and a 22% jump over gpt 5.5 on Agentic Coding Benchmarks is certainly impressive. Obviously still need to verify it for myself to see if it's truely a leap. But am I the only one wondering, "What can I do today that I couldnt do yesterday?" Previously I would think "Oh I wonder if I can finally get it to do X now?" However now I feel like yesterdays models were more that capable to handle nearly any engineering task I paired with it on. Maybe this is the final leap where I can comfortable set up an autonomous coding loop? Maybe.