AgiBot WITA-Omni 全模态模型登顶 DailyOmni,超越 Gemini、豆包、通义千问

AgiBot WITA-Omni Full-Modal Model Tops DailyOmni Global Leaderboard: Beating Google Gemini, ByteDance Doubao, and Alibaba Qwen at Embodied Cross-Modal Understanding

精选理由

AgiBot 发了 WITA-Omni 全模态模型,DailyOmni 上碾压 Gemini 和豆包,还能同时管语音和动作,值得关注。

AI 摘要

AgiBot WITA-Omni 在 DailyOmni 基准上取得 85.21 分,8 项指标中 6 项位列第一。该模型采用 Thinker-Talker-Actor 架构,能够同步处理语音、动作和表情。其性能超越 Google Gemini、字节跳动豆包和阿里巴巴通义千问等竞品。

原文 · pandaily

AgiBot WITA-Omni Full-Modal Model Tops DailyOmni Global Leaderboard: Beating Google Gemini, ByteDance Doubao, and Alibaba Qwen at Embodied Cross-Modal Understanding

AgiBot WITA-Omni scores 85.21 on DailyOmni benchmark, 6 of 8 indicators first place, using Thinker-Talker-Actor architecture that synchronizes speech, action, and expression on a single timeline.