Jev 做长程浏览器任务实测：1/20 对 17/20

Gregor Zunic @gregpr07原推发布于 2026.09.19

在 X 上打开原推

Jev agent got 1/20 vs 17/20 for BrowserCode + Luna on our long horizon task benchmarks. The speed is INSANE. Feels like early Browser Use.(loads of potential, unsolved problems) Browser use is very complex state space search. Very often you just have to think hard or go back. A model with 0 reasoning ability simply can't do that (yet?). Can we get that behavior with better memory + search, without adding a reasoning model? Really hope I can make this work.

这条是引用着另一条写的：「Browser Use + Jev：7 秒查航班，成本约 $0.0039」