Paper introduces Knowledge Index of Noah's Ark benchmark

Arxiv CS.AI (top papers)

New LLM benchmark addresses three issues: scaling-driven designs, flat-payment annotation, and unaudited ranking instability. Aims for disciplinary representativeness and robust evaluation.

llmbenchmarks

Arxiv CS.AI (top papers)·Sheng JinMinghao LiuYunze XiaoZeqi ZhouHeli QiYifan YaoMeishu SongKaijing MaXuan ZhangSicong JiangYizhe LiNingshan MaJie WeiZiniu LiMinglai YangBangya LiuYiming LiangXiao FangQingcheng ZengJiarui LiuRui YangShen Ya

7 days ago