Deep Principle发布基于GLM-5.3训练的科研模型Hydrogen-1.0
动察 Beating AI 报道称，Deep Principle发布Hydrogen-1.0，其在FrontierScience-Research测试中得分38.3，高于报道所列GPT-6 Astra的33.3分。
Loading…
bibibi.ccbibibi.ccLoading…
Connect scattered updates into a story you can understand.
动察 Beating AI 报道称，Deep Principle发布Hydrogen-1.0，其在FrontierScience-Research测试中得分38.3，高于报道所列GPT-6 Astra的33.3分。
Ant Group’s Bailing has open-sourced its large medical model Ling-3.0-flash-Sante, and announced its latest results in multiple professional medical tests.
LLM evaluation blogger “Cat Boss” said that MiniMax M3.1 Flash scored nearly perfectly on old questions but nearly zero after switching to new ones, raising questions over whether it was optimized for old questions.