Event ·Multi-source

Meta Muse Wonder 两款模型实测：与 Claude、GPT-6.1、Gemini 4 正面对比

LMArena 对 Meta 的 Muse Wonder 和 Muse Wonder Full 做了一轮实测，覆盖 3D 场景、动画 HTML 片段和多个网站搭建任务。测试由 Peter Gostev 主持，对比对象包括 Claude Opus 5.5、Sonnet 5.5、Fable 5.1、GPT-6.1 Sol、GPT-6 Astra 和 Gemini 4 Argon。完整对比以视频形式发布在 YouTube。

Current read

Meta 的 Muse Wonder 到底能不能打？这期实测直接拿它和 Claude Opus 5.5、GPT-6.1 Sol 做 3D 场景和建站对比，看完就知道差距在哪。

11 sources27° AI heatLast updated 2026/10/20 00:00:30

Evidence

11 sources

Primary sourcelmarena.ai

2026/10/20 00:00:30View source

Related source 1arXiv cs.AI

2026/10/21 17:11:52View source

Related source 2kimmonismus

2026/10/18 07:23:35View source

Related source 3Bindu Reddy

2026/10/18 21:00:57View source

Related source 4Artificial Analysis

2026/10/19 23:03:30View source

Related source 5WeAreLegora

2026/10/20 15:15:29View source

Related source 6Tw93

2026/10/18 02:46:36View source

Related source 7Browser Use

2026/10/18 05:49:18View source

Related source 8TestingCatalog

2026/10/19 20:07:11View source

Related source 9@koltregaskes

2026/10/19 20:27:00View source

Related source 10Decoder

2026/10/21 17:44:22View source

Conflict check

Dedup data only shows that these sources discuss the same event, not that they agree. There is no structured supporting or refuting evidence yet, so no conflict is inferred automatically.

Open the story