Beginner score
22/100
Competition workspace
适合已有推荐/广告排序模型经验，并能处理用户行为序列、广告文本与图片、上下文特征的开发者或小团队。参赛者还需要能用 AI Studio 账号完成实名认证；希望冲击线下赛的队伍应能准备可运行的推理脚本、环境构建脚本和优化后的模型文件。
Suggested next step
Decide whether this contest fits your current stage before you sink time into the leaderboard.
Beginner score
22/100
Learning value
58/100
Estimated effort
30-90 hours
Metric
Official scoring is published on the Ba…
适合已有推荐/广告排序模型经验，并能处理用户行为序列、广告文本与图片、上下文特征的开发者或小团队。参赛者还需要能用 AI Studio 账号完成实名认证；希望冲击线下赛的队伍应能准备可运行的推理脚本、环境构建脚本和优化后的模型文件。
Taken from the competition's official page.
Model inference environment for entrants during recruitment
Anonymized real user behavior and advertising dataset
If the items below still feel unfamiliar, you usually get a better result by preparing first instead of rushing in.
Transformer 推理优化
广告推荐排序
Python 脚本开发
模型量化
Linux 环境构建
AUC 与 PCOC 指标
The real friction is usually not library usage. It is validation, time allocation, and task framing.
难点在于同时守住排序效果与极低的端到端推理耗时：推理效率或策略效果任一项不达标，整体得分即为 0。你不能通过改动组网策略或用测试集训练来换分，还要把依赖安装、可能的编译步骤和推理流程封装进指定提交包，并满足评测容器的运行限制。
This guide is the best pre-read if you want a cleaner start instead of trial-and-error.
A simple framework for choosing a competition that teaches instead of overwhelming you.
How to Choose Your First AI CompetitionUse these fields to make a quick decision before you dive deeper.
This competition is better treated as a comparison option inside your shortlist before you invest more time.
Sign in to save competitions and build your own shortlist.
Rules, files, submission details, and the live deadline still come from the official page.
These competitions share a similar domain or difficulty level.
Tianchi
LLMTianchi
LLMTianchi
LLMiFlytek Challenge
LLMSeparate what is confirmed from what still needs review. Official rules and deadlines win — report anything that looks wrong.
Official metric is not published on the Baidu AI Studio competition listing; verify scoring on the competition page.