跳到正文
Elon Musk· @elonmusk · X·· 2026-07-10AI 评分82
AI 导读

昨日 xAI 发布 Grok 4.5,侧重智能体编码与知识工作。在全新专有基准 AA-Briefcase 上得分 1328,较 Grok 4.3 提升 578,是非 Anthropic 模型最高分,仅次于 Claude Fable 5(1390)等。任务平均成本 $1.12,比 Claude Opus 4.8 (max) 低 86%;平均耗时 12.4 分钟,约为 Opus 4.8 (max) 的一半,主要因单任务仅 23 轮交互。该基准基于数千个复杂文件中的真实任务。

正文 · AI 翻译

试试 @Grok 4.5!

[引用 @ArtificialAnlys]:Grok 4.5 是 AA-Briefcase 上排名最高的非 Anthropic 模型,将前沿的智能体知识工作能力与领先的成本和时间效率相结合。

昨天 @SpaceXAI 发布了 Grok 4.5,这是一款新的前沿模型,在智能体编码和知识工作方面表现出色。在 AA-Briefcase 上,Grok 4.5 获得了 1328 分,较 Grok 4.3 提升了 578 分,是所有非 Anthropic 模型中的最高分(注:GPT-5.6 尚未发布)。与此同时,它处于成本和时间效率的前沿,平均每个任务成本为 1.12 美元,比 Claude Opus 4.8(max)低 86%;平均每个任务耗时 12.4 分钟,约为 Opus 4.8(max)耗时的一半。

AA-Briefcase 是我们为智能体知识工作新推出的专有基准测试,在包含数千个复杂输入文件的完全私有数据集上,对模型进行真实任务的测试。任务要求产出电子表格、演示文稿和 UI 线框图等交付物,并根据正确性、分析质量和呈现质量综合得出一个 AA-Briefcase Elo 分数。

Grok 4.5 在高推理模式下在 AA-Briefcase 上的关键结果:

➤ 前沿智能体知识工作能力:Grok 4.5 获得 1328 的 AA-Briefcase Elo 分数,是所有非 Anthropic 模型中的最高分,仅次于 Claude Fable 5(1390)、Claude Sonnet 5(max,1390)和 Claude Opus 4.8(max,1354)。在 AA-Briefcase 的三个评分维度上,Grok 4.5 在客观评分标准和分析质量方面表现最强,而呈现质量相对较弱。它的总体评分标准通过率达到第二高(40.7%),仅次于 Claude Fable 5(56%)和 Claude Sonnet 5(42.3%)。

➤ 领先的成本效率:Grok 4.5 平均每个 AA-Briefcase 任务的成本为 1.12 美元,处于成本-性能帕累托前沿。这比同级别的模型(如 Claude Opus 4.8(max,8.26 美元)和 GLM 5.2(max,1.71 美元))更具成本效益。

➤ 更快的任务完成速度:Grok 4.5 平均每个 AA-Briefcase 任务耗时 12.4 分钟,同样处于速度-性能前沿。它比 Claude Opus 4.8(max,23.9 分钟)和 Claude Sonnet 5(max,36.9 分钟)快得多,主要原因是轮次使用更少。Grok 4.5 平均每个任务仅需 23 轮,约为 GLM 5.2(max,56 轮)的 40%,以及 Claude Sonnet 5(max,183 轮)的 13%。

祝贺 @SpaceXAI、@cursor_ai 和 @elonmusk 取得令人印象深刻的发布成果!

引用Artificial Analysis@ArtificialAnlys
Grok 4.5 is the top non-Anthropic model on AA-Briefcase, combining frontier agentic knowledge work capabilities with leading cost and time-efficiency Yesterday @SpaceXAI released Grok 4.5, a new frontier-level model with strengths in agentic coding and knowledge work. On AA-Briefcase, Grok 4.5 scores 1328, a +578 improvement over Grok 4.3 and the highest score of any non-Anthropic model (note that GPT-5.6 not released yet). It achieves this while sitting on the cost and time efficiency frontier, averaging $1.12 per task, 86% lower than Claude Opus 4.8 (max), and 12.4 minutes per task, around half the time of Opus 4.8 (max). AA-Briefcase is our new proprietary benchmark for agentic knowledge work, testing models on a fully private dataset of realistic tasks across thousands of complex input files. Tasks require deliverables like spreadsheets, presentations, and UI mock-ups, with performance combined into a single AA-Briefcase Elo across correctness, analytical quality, and presentation quality. Key results for Grok 4.5 with high reasoning on AA-Briefcase: ➤ Frontier agentic knowledge work capabilities: Grok 4.5 achieves an AA-Briefcase Elo of 1328, the highest score of any non-Anthropic model, behind only Claude Fable 5 (1390), Claude Sonnet 5 (max, 1390), and Claude Opus 4.8 (max, 1354). Across the three AA-Briefcase scoring axes, Grok 4.5 is strongest on objective rubric criteria and analytical quality, with comparatively weaker presentation quality. It achieves the second-highest overall rubric pass rate (40.7%), behind Claude Fable 5 (56%) and Claude Sonnet 5 (42.3%) ➤ Leading cost efficiency: Grok 4.5 averages a cost of $1.12 per AA-Briefcase task, placing it on the cost-performance Pareto frontier. This is much most cost effective than peer models such as Claude Opus 4.8 (max, $8.26) and GLM 5.2 (max, $1.71) ➤ Faster task completion: Grok 4.5 averages 12.4 minutes per AA-Briefcase task, also placing it on the speed-performance frontier. It is much faster than Claude Opus 4.8 (max, 23.9 min) and Claude Sonnet 5 (max, 36.9 min), primarily due to lower turn use. Grok 4.5 averages just 23 turns per task, ~40% of GLM 5.2 (max, 56) and ~13% of Claude Sonnet 5 (max, 183) Congratulations to @SpaceXAI, @cursor_ai, and @elonmusk on the impressive release!
在 X 查看被引用的帖子

来源:Elon Musk · x.com