Meta's Muse Wonder Full hits 57.5% on SWE-Marathon, beating Opus 5.5 and GPT-6 Astra
altryne · x · 2026-10-13
Zuckerberg announced Muse Wonder and Muse Wonder Full, Meta's new frontier models for personal and professional agentic work. Meta reports 79.0% on DeepSWE (vs 74.2% for Claude Opus 5.5, 74.1% for GPT-6 Astra) and 57.5% on SWE-Marathon (vs 46.3% and 42.5%). New Active Memory and Active Focus mechanisms sustain long agent work; trained at the gigawatt-scale Prometheus datacenter. Available now via Meta Model API and Muse Code.
Related event: Meta Unveils Muse Wonder, Its Most Capable Frontier Model(92 posts)→
More from Models
- ReplaySSM ships in GLM-5.3-Flash and Kimi-K3, speeding decoding up to 2.1x — SonglinYang4 · 2026-10-13
- AI2's TutorMoments eval: GPT-6 models over-help least, detailed prompts beat "tutor well" — allen_ai · 2026-10-13
- AI2's TutorMoments benchmarks AI tutors on 520 real moments; human tutors score 0.458 — allen_ai · 2026-10-13
- Allen AI's TutorMoments Benchmark Finds LLM Tutors Over-Help Students — allen_ai · 2026-10-13
- DeepSeek's flash endpoint may be quietly testing a new model, users speculate v4.1-pro — teortaxesTex · 2026-10-13
- 3D game demos hint at AI creativity that transfers to CAD, docs and UI tasks — Angaisb_ · 2026-10-13