Leaked benchmarks show Meta's rumored Muse Wonder leading on agentic and personal-AI evals
RihardJarc · x · 2026-10-13
An unverified leak suggests Meta is preparing a new model called Muse Wonder with "active focus," trained on specialized datasets for knowledge work, health, finance and legal. The attached benchmark table claims:
- Muse Wonder Full tops the Personal Superintelligence Index at 59.1, ahead of Claude Fable 5.1, GPT-6 Astra and Claude Opus 5.5
- Strongest margins on Harvey LAB-AA (13.1 vs single digits), plus leads on AutomationBench-AA, DeepSWE 1.1 and SWE-Marathon
- Still trails Claude Opus 5.5 or GPT-6 Astra on HealthBench Pro, OSWorld, Terminal-Bench and ProgramBench; Artificial Analysis Index of 56 vs Opus 5.5's 58
Meta has not confirmed the model; treat the numbers as unverified.
Related event: Meta Unveils Muse Wonder, Its Most Capable Agentic Frontier Model(88 posts)→
More from Models
- Muse Wonder scores ~42% on senior engineer benchmark vs Sol 6.1's 71% — danshipper · 2026-10-13
- Zuckerberg unveils Muse Wonder, a frontier model family for agentic work — RebeccaBellan · 2026-10-13
- OpenAI's Decisions API hits 98.1% F1 vs agent's 93.5% at 1/7 cost and 28x lower p90 latency — OpenAIDevs · 2026-10-13
- Alexandr Wang admits Muse Wonder wasn't trained on 3D game demos, insists it excels at real coding — alexandr_wang · 2026-10-13
- Leaked terms suggest X Premium + Grok + Cursor bundled subscription: social, AI and IDE in one plan — ns123abc · 2026-10-13
- X publishes legal terms for bundled X Premium + Grok + Cursor subscription — ns123abc · 2026-10-13