Meta Muse Ember 重写 Code Arena WebDev 价格性能前沿
Meta 的 Muse Ember 在 3 美分价位拿到 1608 分,比同价位旧最佳高 170 分,胜率约 73%。做 WebDev 生成的团队选模型时可以看看这份价格性能曲线,低价区间的格局变了。
LMArena 发布最新一期 Code Arena: WebDev 价格性能追踪,五款新模型进入 Pareto 前沿:Anthropic 的 Claude Fable 5.2 (xHigh)、Google DeepMind 的 Gemini 4 Carbon (High)、Moonshot 的 Kimi K3.1 Pro (Max)、OpenAI 的 GPT-6.1 Terra (Max) 和 Meta 的 Muse Ember (Max)。其中 Muse Ember 对前沿的移动幅度最大。
在约 3 美分一次回答的价位上,Muse Ember 拿到 1608 分,而此前同价位最佳成绩为 1438 分。按 Arena 的 Elo 胜率估算,这一分差意味着 Muse Ember 约有 73% 的概率战胜旧冠军。Meta 由此在 WebDev 场景的低价区间建立了新的性价比标杆。
文章同时指出行业整体节奏在加快:头部分数的更新速度达到此前的 3 倍,而 4 月份的最佳成绩如今只需 1/20 的成本就能复现。对开发团队而言,WebDev 编码任务的单位成本正以远快于模型能力提升的速度下降,选型时价格性能曲线比绝对分数更具参考价值。
Muse Ember by @AIatMeta has reshaped the Pareto frontier for Code Arena: WebDev. In our last article, we put the AI race under the spotlight and tracked how price-performance trade-offs improved on Code Arena: WebDev from April to October 2026. But competition never sleeps. Since then, five new models have joined the frontier: - Claude Fable 5.2 (xHigh) by @AnthropicAI - Gemini 4 Carbon (High) by @GoogleDeepMind - Kimi K3.1 Pro (Max) by @Kimi_Moonshot - GPT-6.1 Terra (Max) by @OpenAI - Muse Ember (Max) by @AIatMeta Of the five, Muse Ember moved the frontier the most. At about 3 cents an answer, it scores 1608, against 1438 for the previous best at that price. That means it would win about 73% of the time. Curious how we got here? Full article below.
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 AI developer toolchains, coding agents, and engineering workflows and US-China foundation model benchmarks and commercialization comparison. Key entities and technical topics under continuous tracking include Muse Ember, Claude Fable, Gemini 4 Carbon, Kimi K3.1 Pro.
Source attribution: curated from lmarena.ai (@lmarena_ai).