Cua-Bench-S1：面向 Jev 等决策模型的电脑操作基准

trycua 发布 Cua-Bench-S1，首个评测 Jev 等 computer-use 决策模型的基准。

Y Combinator

@ycombinator2026.09.22收录原推发布于 2026.09.22

Y Combinator @ycombinator原推发布于 2026.09.22

RT @trycua: 1/ Introducing Cua-Bench-S1, a benchmark for decision models built for computer use, including Jev. We're releasing the first…

x.com/ycombinator/status/2102154832228565065采集于 2026.09.22 10:31