Muse Wonder research blog drops: more detail on Alexandr Wang's agentic model benchmarks
alexandr_wang · x · 2026-10-13
Following the Muse Wonder announcement, Alexandr Wang shared a link to the team's research blog with more detail on the model's agentic and coding benchmark evaluations.
The earlier self-reported charts put Muse Wonder Full ahead of Claude Opus 5.5 and GPT-6 Astra on Personal Superintelligence Index (59.1%), AutomationBench-AA (45.4%), SWE-Marathon (57.5%) and DeepSWE (79.0%).
Related event: Meta Unveils Muse Wonder, Its Most Capable Frontier Models Yet(45 posts)→
More from Models
- Meta launches Muse Wonder models, tops SWE-Marathon at 57.5% — acbuller · 2026-10-13
- 60.6% of LLM theorem rewrites silently drop hidden hypotheses, study finds — MFarajtabar · 2026-10-13
- Meta's superintelligence lab launches Muse Wonder, a frontier model tuned for personal agents — alexandr_wang · 2026-10-13
- Muse Code CLI goes live with one-line curl install for Muse Wonder — alexandr_wang · 2026-10-13
- Meta's Wonder Full Debuts #5 on Vals Index, Outranking Every OpenAI Model — airesearch12 · 2026-10-13
- Mysterious new model Muse Wonder appears on LMArena in Battle and Agent modes — arena · 2026-10-13