Meta 发布 Muse Ember (Max)，登顶 Agent Arena 高效模型榜首
Meta 新发的 Muse Ember 在 Agent Arena 上分数和 GPT-6 Luna、Claude Haiku 5.5 差不多，但单任务只要 $0.02，速度快十几倍。做智能体或跑批量任务的开发者可以直接看这组成本数据，选型时很实用。
Meta 的 AI 团队推出 Muse Ember，定位为旗下最小、最高效的模型，主打复杂推理执行与日常智能体工作，能跨应用执行工作流、按序调用工具、跑测试并做针对性代码修复。
Muse Ember (Max) 在 Agent Arena 基准中以 +1.7% 净改进位列第 25 名，基于 6000 个真实智能体会话数据测得，单任务成本约 $0.
02，速度约 0.5 分钟/任务，输出 11.
6K tokens。对比之下，GPT-6 Luna (Max) 净改进 +1.
6%、成本 $0.09/任务、耗时 6 分钟、输出 41.
2K tokens；Claude Haiku 5.
5 (High) 净改进 +0.5%、成本 $0.
08/任务、耗时 1.8 分钟、输出 24.
3K tokens。三者性能接近，但 Ember 的单任务成本约为对手的 1/4，速度比 Luna (Max) 快约 12 倍，比 Haiku 5.
5 快 3.5 倍，输出 tokens 分别少 72% 和 52%。
该模型配备 1M-token 上下文窗口，原生支持文本、图像、音频和视频多模态输入，可处理大型文档集合。对需要大量智能体任务但预算敏感的团队来说，成本与速度差距比分数差距更有意义。
Muse Ember (Max) by @AIatMeta lands in Agent Arena as the most capable and efficient : +1.7% net improvement at about $0.02 per task, roughly 4x less than GPT-6 Luna (Max) and Claude Haiku 5.5, across 6k real-world agentic sessions from our global community. How it stacks up against other efficient models - #25 Muse Ember (Max): +1.7% | $0.02/task | 0.5 min/task | 11.6K output tokens - #26 GPT-6 Luna (Max): +1.6% | $0.09/task | 6 min/task | 41.2K output tokens - #29 Claude Haiku 5.5 (High): +0.5% | $0.08/task | 1.8 min/task | 24.3K output tokens Performance is on par across the three, but Ember's median task costs roughly 4x less, finishes about 12x faster than Luna (Max) and 3.5x faster than Haiku 5.5, and uses 72% and 52% fewer output tokens. Congrats to the @AIatMeta team, @alexandr_wang and @finkd on this impressive release! AI at Meta @AIatMeta Today we're introducing Muse Ember, our smallest and most efficient model, built for complex reasoning execution and everyday agent work. Muse Ember can carry workflows across apps, call tools in sequence, run tests and make targeted code fixes. With a 1M-token context window and native understanding of text, images, audio and video, it can also work across large document sets and varied inputs. 🔗 View Quoted Tweet📊 5 ⚡
This report is categorized under AITOP's "Models" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to US-China foundation model benchmarks and commercialization comparison and AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include Muse Ember, Meta, Agent Arena, GPT-6 Luna.
Source attribution: curated from lmarena.ai (@lmarena_ai). Cross-source corroboration: 11 independent sources have covered this development (including Blognone, IT之家, rohanpaul_ai), confirming industry-wide signal strength.
