Muse Wonder Full
The larger Muse Wonder variant, released to Muse Code subscribers for extended software work and professional agents. It is the tested variant underlying Meta’s family catastrophic-risk assessment.
0 comments · 0 votes
Sign in to join the discussion →
No comments yet. Start the discussion.
Why this model scores 86.6
Difficult-task results support capability 94 and long-horizon coding autonomy 94. Subscriber reach limits deployment to 70. Cyber/bio proxies support misuse 90. Control difficulty 78 balances refusals and low tested misalignment against incomplete coverage and system-level dependencies. Vendor risk labels are not guarantees.
News tied to Muse Wonder Full
The model score of 86.6 rates this model's risk profile. The overall Doom Index of 69.0 measures the complete temporally weighted evidence record. These values answer different questions.
Each article's current Doom Index contribution is divided equally among the exact models named on that article. This prevents multi-model evidence from being claimed in full on several model pages. Model risk scores use a bounded temporal offset around their technical profile, but never feed back into the overall index.
Meta launches Muse Wonder and Muse Wonder Full for sustained agent work
Meta released Muse Wonder through its model API and Muse Code, and Muse Wonder Full to Muse Code subscribers. The models emphasize persistent context, recovery after blockers and extended coding tasks. Meta reports strong agent evaluations; wider consumer rollout and safety-report additions were still forthcoming in the launch announcement.
- Full item contribution
- +0.11
- Muse Wonder Full equal share
- +0.05
Model score history
-
R1
Doom Score 86.6
Backfilled the separately named Full variant and its restricted launch access rather than merging it with Wonder.
30 Oct 2026