Meta 发布 Muse Ember（Max），登顶 Code Arena 小模型榜首
Exciting news: @AIatMeta's Muse Ember (Max) is the highest-performing small model in the Code Arena:...
Meta 这个 Muse Ember 单任务成本只要 3 美分，同样的 API 定价下比 Haiku 和 Luna 省一半以上，还能跨应用跑智能体工作流。如果你的 agent 要批量跑代码任务，这份成本对比表很值得算一算。
Meta 在 Code Arena: WebDev 排行榜上，Muse Ember (Max) 以 1608 分成为最高分小模型，超过 Anthropic 的 Claude Haiku 5.5 (High) 的 1595 分（第 35 名）和 OpenAI 的 GPT-6 Luna (Max) 的 1578 分（第 42 名）。三个模型的 API 定价相同，均为每百万输入/输出 token 0.10/0.50 美元，但 Ember 的单任务中位成本为 0.03 美元，是 Luna（0.06 美元）的 1/2、Haiku（0.11 美元）的约 1/3.7，使其进入 Pareto 前沿。
Muse Ember 定位为 Meta 最小、最经济的模型，面向复杂推理执行和日常智能体工作，可以在应用之间执行工作流、按顺序调用工具、运行测试并做针对性代码修复。它配备 1M token 上下文窗口，原生支持文本、图像、音频、视频四种模态，可处理大型文档集和混合输入。
Arena 团队实测显示，Ember 完成约 25 个复杂生成任务，每个任务约 2 分钟，总花费仅 1 美元。对于做智能体和代码生成的开发者，同价位下更低的单任务成本意味着可以大规模跑长工作流而不用换模型或涨价预算。
Exciting news: @AIatMeta's Muse Ember (Max) is the highest-performing small model in the Code Arena:...
Exciting news: @AIatMeta 's Muse Ember (Max) is the highest-performing small model in the Code Arena: WebDev with 1608 pts, outperforming two leading small models from Anthropic and OpenAI: - Claude Haiku 5.5 (High): #35 , 1595 pts - GPT-6 Luna (Max): #42 , 1578 pts At a 1608 score at a median cost of $0.03 per task, this puts Ember on the Pareto frontier. Neither Haiku 5.5 nor Luna makes it. Despite all three models having the same API pricing of $0.10/$0.50 per million input/output tokens, Ember's median cost per task is 2× lower than Luna ($0.06) and 3.7× lower than Haiku ($0.11). In our own testing, Ember demonstrated impressive speed and efficiency, completing 25 complex generations in 2 mins per task, at a total cost of just $1. Huge congrats to @alexandr_wang and the @AIatMeta team on this impressive release! A major step forward for small models that deliver strong real-world coding capabilities at a fraction of the cost. 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📊 10 ⚡
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, Claude Haiku, GPT-6 Luna.
Source attribution: curated from lmarena.ai (@lmarena_ai).
