AI 热点

Arena:Meta Muse Ember 改写 Code Arena WebDev 性价比前沿

Arena更新于 11月17日 03:49

Muse Ember by @AIatMeta has reshaped the Pareto frontier for Code Arena: WebDev.

AI 导读

Arena 称 Meta 的 Muse Ember 改写了 Code Arena: WebDev 的帕累托前沿。该模型每答案约 3 美分时得分 1608,此前同价位最佳为 1438,按此计算约 73% 的对局会胜出。Arena 还列出同期进入前沿的五款模型,包括 Claude Fable 5.2 (xHigh)、Gemini 4 Carbon (High)、Kimi K3.1 Pro (Max)、GPT-6.1 Terra (Max) 和 Muse Ember (Max)。

推荐理由

精选AI 评分 67

Arena 用价格与得分对比展示五款新模型在 WebDev 榜单上的位置变化,可据此判断同价位下的性价比差异。

主题

标签

引用

Arena.ai

@arena

随着最高分数提升至原来的3倍,四月的最佳成绩成本降低了20倍。https://t.co/oKOvVP2X3A

查看原文

As the top scores move 3x faster, April’s best costs 20x less. https://t.co/oKOvVP2X3A

查看原帖

正文

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.

来源

Arena