Xiaokang Chen(@PKUCXK):Looking at today's LLM / Multimodal LLM benchmarks is like looking at an elite student's exam scores: a high score doesn't guarantee real-world capability. The focus must shift from leaderboards to usability, reliability, and seamless workflow integration.

Xiaokang Chen

@PKUCXK

Researcher in Multimodal Team @deepseek_ai Previously Bachelor & Ph.D at Peking University @PKU1898 Opinions are my own.

가입 June 2022

63 팔로잉 중 6.4K 팬

Xiaokang Chen@PKUCXK

2025.10.29 08:27

Looking at today's LLM / Multimodal LLM benchmarks is like looking at an elite student's exam scores: a high score doesn't guarantee real-world capability. The focus must shift from leaderboards to usability, reliability, and seamless workflow integration.