Meta Muse Ember 在 Agent Arena 效率模型对比中全面领先
The race among efficient models built for real work has a new leader: Muse Ember by @AIatMeta. Embe...
Meta 的 Muse Ember 在 Agent Arena 实测里同时拿下速度、性能和成本三项第一:27 秒一个任务,比 GPT-6 Luna 快约 13 倍,单价 1.9 美分还不到 Claude Haiku 5.5 的三分之一。跑智能体任务、在意延迟和账单的开发者可以直接看数据选型。
Meta 发布的 Muse Ember 在 Agent Arena 效率模型对比中全面领先 GPT-6 Luna 和 Claude Haiku 5.5。Ember(Max)单任务耗时 27 秒,Luna(Max)为 5.8 分钟,Haiku 5.5(High)为 1.9 分钟。性能方面,Ember 的 Net Improvement 得分为 +2.3%,高于 Luna 的 +1.4% 和 Haiku 5.5 的 +0.4%。
成本差距同样明显:Ember 每任务 1.9 美分,Luna 为 7.0 美分,Haiku 5.5 为 6.9 美分,约为两者成本的三分之一以下。速度上 Ember 比 Luna 快约 13 倍。对比基于 Agent Arena 的真实任务数据,评测还包含 Ember 在 Work 场景下的 steerability 得分,以及用户用 Muse Ember 实际交付的任务样本。对需要在成本和延迟敏感场景跑智能体任务的开发者来说,这份榜单提供了直接可用的选型参考。
The race among efficient models built for real work has a new leader: Muse Ember by @AIatMeta. Embe...
The race among efficient models built for real work has a new leader: Muse Ember by @AIatMeta . Ember (Max) leads on every dimension against GPT-6 Luna (Max) from @OpenAI and Claude Haiku 5.5 (High) by @AnthropicAI : - Speed: 27s per task vs 5.8 min and 1.9 min - Performance: +2.3% Net Improvement (Agent Arena score) vs +1.4% and +0.4% - Cost: 1.9¢ per task vs 7.0¢ and 6.9¢ That’s ~13x faster than Luna and less than a third of the cost of either. Below find more analysis on Ember’s steerability score across Work, and a look at what real-world tasks users are shipping with Muse Ember in the Agent Arena.📊 1 ⚡
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, GPT-6, Claude Haiku 5.5, Agent Arena.
Source attribution: curated from lmarena.ai (@lmarena_ai).