AI 导读
Gemini 3.8 Flash 在 Artificial Analysis 的智能体知识工作评测 AA-Briefcase 上取得 1213 Elo,较 Gemini 3.7 Flash 的 1134 提升 79 分。
正文
On AA-Briefcase, our flagship agentic knowledge work evaluation, Gemini 3.8 Flash scores an Elo of 1213. AA-Briefcase tests models on a fully private dataset of realistic tasks across thousands of complex input files, with performance combined into a single AA-Briefcase Elo based on correctness, analytical quality, and presentation quality. Gemini 3.8 Flash improves its overall AA-Briefcase Elo by 79 points, compared to Gemini 3.7 Flash (1134), driven mostly by higher rubric score (objective criteria) and Analytical Quality Elo, rather than improved Presentation Quality
来源:@ArtificialAnlys · x.com