Meta Muse Ember 在 Code Arena WebDev 以 1608 分成为最强小模型
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 model
Arena.ai 称 Meta 的 Muse Ember（Max）在 Code Arena WebDev 榜单以 1608 分成为得分最高的小模型，超过 Claude Haiku 5.5（1595 分）和 GPT-6 Luna（1578 分）。Ember 单任务中位成本为 0.03 美元，低于 Luna 的 0.06 美元和 Haiku 的 0.11 美元，三款模型 API 定价同为每百万输入/输出 token 0.10/0.50 美元。Arena 自测中，Ember 每任务 2 分钟完成 25 次复杂生成，总成本 1 美元。
查看原帖今天，我们推出 Muse Ember，这是我们最小、最高效的模型，专为复杂推理执行和日常智能体工作而打造。 Muse Ember 可以跨应用承载工作流、按顺序调用工具、运行测试并进行有针对性的代码修复。凭借 100 万 token 的上下文窗口以及对文本、图像、音频和视频的原生理解能力，它还能处理大型文档集和多样化的输入。
查看原文
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.
正文
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.