MMLU vs 豆包：怎么选？

关于 MMLU

Agentic coding tools receive goals written in natural language as input, break them down into specific tasks, and write or execute the actual code with minimal human intervention. Central to this process are agent context files ("READMEs for agents") that provide persistent, project-level instructions. In this paper, we conduct the first large-scale empirical study of 2,303 agent context files from 1,925 repositories to characterize their structure, maintenance, and content. We find that these files are not static documentation but complex, difficult-to-read artifacts that evolve like configuration code, maintained through frequent, small additions. Our content analysis of 16 instruction types shows that developers prioritize functional context, such as build and run commands (62.3%), implementation details (69.9%), and architecture (67.7%). We also identify a significant gap: non-functional requirements like security (14.5%) and performance (14.5%) are rarely specified. These findings indicate that while developers use context files to make agents functional, they provide few guardrails to ensure that agent-written code is secure or performant, highlighting the need for improved tooling and practices.

LingBot-Map is a feed-forward 3D foundation model that reconstructs scenes from video streams using a geometric context transformer architecture with specialized attention mechanisms for coordinate grounding, dense geometric cues, and long-range drift correction, achieving stable real-time performance at 20 FPS.

Agents-A1, a 35B Mixture-of-Experts Agentic Model, achieves trillion-parameter-level performance through long-horizon trajectory scaling and heterogeneous agent ability scaling via a three-stage training approach involving supervised fine-tuning, domain-level teacher models, and multi-teacher distillation.

关于 豆包 豆包是字节跳动推出的AI智能助手，目前已从基础的问答对话工具发展为具备复杂任务执行能力的生产力平台。截至2026年6月，豆包大模型日均Token调用量已突破180万亿，月活跃用户约3.45亿，稳居国内消费级大模型用户规模榜首。

一、核心功能

豆包的功能体系可划分为三大板块：

1. 基础AI能力（免费版核心）

免费版用户可正常使用上述全部功能，且可在一定额度内体验办公任务模式（搭载豆包2.1 Turbo模型）。

2. 办公任务模式（专业版核心突破）

2026年6月24日，豆包正式推出豆包专业版，上线基于Agent驱动的“办公任务模式”。与传统对话模式不同，该模式能够：

1. 理解复杂工作目标，自主拆解为多步任务
2. 调用各类工具完成全流程执行（本地电脑、浏览器、Office套件、飞书等）
3. 后台运行长任务，用户可脱身处理其他工作
4. 定时执行重复任务，如每日日报、定期报告汇总

关键能力实测表现：

3. 智能体与Skills（技能生态）

豆包支持智能体（Agent）创建与分享，用户可根据学习、工作、创作、生活等场景定制专属智能体。

“Skills（技能）”是另一重要能力，首批包括文档、表格、PPT、创意设计、操作浏览器、可视化讲解等，以及金融行业专业技能。用户还可以创建、安装自己的专属技能。