Dongmodi Bench Hackathon

Registration closed · Similar hackathons still open

All open hackathons →

Not sure which to join? Get 1:1 help →

Dongmodi Bench Hackathon
Screenshot of the source page
EvaluationAgent

About this hackathon

Spend 30 hours writing an exam for LLMs and define which agent capabilities really matter. A Useful track for real tasks and a Fun track for role-play and game evals; build the benchmark, then test five models.

Status
Deadline
2026-08-22
Starts
2026-08-22
Who
Open to all
Level
Intermediate
Prize
Mac mini grand prize; Bambu Lab, DJI, Insta360 prizes; Kimi and Qwen API credits
Size
—
Format
In person · Beijing · China
Location
Beijing

Browse similarHackathons in BeijingAI hackathonsAI Agent hackathonsHackathons in August 2026

Original listing (Chinese)

The full original listing below is in Chinese, as published in the Hack123 newsletter.

30小时给大模型出一套考题,⁠‍‍‌‍‍‌‍‍‍‍‌‍‍‍‌‌‌‍‌‌‌‍‌‍⁠自己定义 Agent 真正重要的能力。

看点:有用赛道测真实任务;整活赛道做角色和游戏评测;先搭 Bench,再用5个模型实测

奖金:Mac mini 大奖;拓竹、大疆、影石等奖品;Kimi、Qwen API额度

截止日期:8月22日12:00开赛,8月23日18:00结束(北京)

Summarized from the Chinese “Beginner Hackathon Series” newsletter. Eligibility, dates and prizes are subject to the organizer’s official page.