Mercor 发布 APEX-Agents 榜单,Gemini 4 Carbon 以 90.4% 均值登顶
RT Mercor: Gemini 4 Carbon debuts at #1 on APEX-Agents, and it's the only model on the leaderboard with a mean above 90%. 🥇Gemini 4 Carbon - 84.2% ...
AI 导读
Mercor 发推称 Gemini 4 Carbon 登顶 APEX-Agents 榜首,Pass@1 为 84.2%,均值 90.4%,是榜单上唯一均值超过 90% 的模型,Gemini 4 Argon 与 Claude Sonnet 5.5 分列二三位。