Meta 发布 Muse Ember：36 分追平 Claude Haiku 5.5，成本仅三分之一
Meta 这次的思路很明确：知识面窄没关系，把幻觉率砍半、把成本压到 $0.14 一任务，专攻自动化执行。在 Terminal-Bench 上它反超 Haiku 5.5，自家的 Muse Code 里更是领先 Claude Code 和 Codex。跑批量任务的团队可以重点看看。
Meta 推出高效档新模型线 Muse Ember，在 Artificial Analysis Intelligence Index 上得 36 分，与 Claude Haiku 5.5 (max) 持平，但 Cost per Task 仅 $0.14，约为后者的三分之一。xhigh 档得 34 分，成本 $0.12。定价为每百万 tokens 输入 $0.10、缓存输入 $0.004、输出 $0.50，与 Claude Haiku 5.5 和 GPT-6 Luna 相同。
技术上，Muse Ember (max) 在 Terminal-Bench 4.0 上得 40.9%，超过 Claude Haiku 5.5 (max) 的 32.8%，但在 FrontierCode 2.0 上以 27.2% 落后于对方的 34.9%，智能体编程表现两极。在 AutomationBench-AA 上得 68.1%，与 Muse Wonder (max) 持平；GDP.pdf 子项 22.8% 高于 Haiku 5.5 的 20.8%，AA-Briefcase 则以 1521 Elo 落后于 1574。在自家 Muse Code 智能体中，其 Coding Agent Index 得 46 分，高于 Claude Code 中的 Haiku 5.5（37）和 Codex 中的 GPT-6 Luna（31）。
知识覆盖是主要短板：AA-Omniscience 准确率 21.1%，低于 Haiku 5.5 (max) 的 34.7% 和 Gemini 3.8 Flash (high) 的 50.5%，主因是拒答 64% 的问题，幻觉率因此压到 17.4%，约为 Haiku 5.5 的一半。与同门 Muse Wonder (max) 相比，它落后 8 分，但成本仅为后者的约 1/50（$0.14 vs $6.95），走的是低成本自动化执行路线。
Meta's newest model Muse Ember scores 36 on the Artificial Analysis Intelligence Index, matching Claude Haiku 5.5 (max) at a third of the Cost per Task
Muse Ember is Meta's newest efficient-tier model line, with the same input and output token prices as Claude Haiku 5.5 and GPT-6 Luna
Key Takeaways:
➤ On the Intelligence Index vs. Cost per Task Pareto frontier at both max and xhigh effort. Muse Ember (max) is the cheapest model scoring 36 or higher, at $0.14 per task, and Muse Ember (xhigh) scores 34 for $0.12. Claude Haiku 5.5 (max) costs almost 3x more at $0.41 for the same score as Muse Ember (max). Muse Ember (max) is also about 4x cheaper than DeepSeek V4.1 Flash 1017 (max, 33, $0.60) and GLM-5.3-Flash (28, $0.58)
➤ 8 points behind Muse Wonder for about 1/50th of the Cost per Task. Muse Wonder (max) scores 44 at $6.95 per Intelligence Index task
➤ Stands out on AutomationBench-AA. Muse Ember (max) scores 68.1% on AutomationBench-AA, level with Muse Wonder (max), and beats Claude Haiku 5.5 (max) on GDP.pdf (22.8% vs 20.8%), but trails it on AA-Briefcase (1521 vs 1574 Elo)
➤ Mixed in agentic coding in our Intelligence Index evaluations. It beats Claude Haiku 5.5 (max) on Terminal-Bench 4.0 (40.9% vs 32.8%) but trails it on FrontierCode 2.0 (27.2% vs 34.9%)
➤ Ahead of similarly priced models when running in its own coding agent. In Muse Code, Muse Ember (max) scores 46 on the Artificial Analysis Coding Agent Index, ahead of Claude Haiku 5.5 in Claude Code (max, 37) and GPT-6 Luna in Codex (max, 31)
➤ Knowledge is the main weakness, but it rarely hallucinates. Its AA-Omniscience accuracy of 21.1% is the lowest of the similarly intelligent models we compared, against 34.7% for Claude Haiku 5.5 (max) and 50.5% for Gemini 3.8 Flash (high). This is mostly because it declines to answer 64% of questions, which keeps its hallucination rate at 17.4%, half of Claude Haiku 5.5’s (max)
Other details: ➤ Pricing: $0.10 input / $0.004 cached input / $0.50 output per 1M tokens ➤ Reasoning effort: results shown at max effort, with xhigh also on the Intelligence vs. Cost chart ➤ Availability: Meta's first-party API and Muse Code
本条情报归属 AITOP「模型」核心栏目，重点聚焦北美前沿实验室与硅谷科技巨头。在跨区域产业观察坐标中，该动态直接关联「中美大模型技术代差与商业化对照」「AI 开发者工具链、Coding Agent 与工程化实践」研究主线，反映出当前技术演进与商业落地的最新风向。涉及核心实体与技术议题包括：Muse Ember、Meta、Claude Haiku 5.5、GPT-6 Luna，读者可通过下方标签进入对应专题页查阅历史脉络与关联对比。
信源核验说明：本文原始线索采编自「Artificial Analysis」（@ArtificialAnlys），经 AITOP 多维评分管线结构化提炼。
