ByteBrief
We're a portrait publication through and through. Turn your phone back and your briefing picks up right where you left it.
(We tried widescreen once. It wasn't us.)

Baidu launched DuMateBench, a leaderboard measuring AI agents' real-world task completion. It includes over 200 office tasks across six categories, evaluating task understanding, tool use, continuous execution, and final-result delivery. The benchmark uses open interfaces for standardized testing of different models.
Tap to vote and see what everyone thinks.
Summary by ByteBrief