Signal
Advertise
Signal
Advertise
Sign in
Submit
Discover trends that matter
Trending repositories
Daily
Weekly
Monthly
Yearly
Live mentions
Topics
GitHub trending
Repositories
Developers
Insights
Stats
Log in
ktwu01/benchmark-radar — GitHub trending stats & insights | Trendshift
Featured
open-connector
ktwu01/benchmark-radar
#
Curated list
Daily evidence-first radar for AI benchmarks, evaluations, datasets, and data quality.
Visit GitHub
Like ktwu01/benchmark-radar, 0 likes
0
Python
20
9
3 contributors
MIT License
website
Social mentions
Recent discussions about this repository across the web
我从 GitHub、Hugging Face、OpenAlex 等 11 个来源抓了 4000+ 条 benchmark/eval/dataset 数据,如果需要寻找 related work 或找到适合eval自己的agent 的 bench 或者关注最新的 eval 进展,可以看这里: ,每天更新,并支持一键导出数据
@ktwu01 · x.com
benchmark-radar code更新 0. 一键导出,方便大家搜索全网benchmarks,目前已经收集20天,3995 个例子 1. 新增 rss 订阅方式,用rss来看每天的benchmark日报 2. 在原有8个API source例如Github huggingface的基础上,新增Alina的信源 code:
@ktwu01 · x.com
Agent benchmark 看起来像在测“AI 能否推进人类知识前沿”,实际上大多还在测“AI 能不能把作业做完”。 目前主体是 L2 执行和 L3 复现,L4 再发现刚刚出现;真正创造未知知识或方法的 L5,本周依然空缺。
@ktwu01 · x.com
The unit is the document. If one card reports AIME at pass@1, consensus@64, and with tools, it still contributes one adoption. A long appendix cannot outvote another vendor.
@ktwu01 · x.com
AI researchers deserve an award for paper titles 😂 “Malice in Agentland: Down the Rabbit Hole of Backdoors in the AI Supply Chain.” 🐇 I came across it while curating today’s Benchmark Radar:
@ktwu01 · x.com
Repository activities
repository's daily and monthly activities across stars, forks, merged PRs, issues, and closed issues