UCSD Hao AI Lab 发布零样本机器人操作框架 ORA v0.1
Which models are good at robot use? We ran six open models with the same prompt and tools and compared the result with public benchmarks. We found t lines up be
AI 导读
UCSD Hao AI Lab 发布开源零样本机器人操作框架 ORA v0.1,DeepSeek V4.1-Flash 在 RoboDojo 和 RoboTwin 上分别达到 39.9% 和 79.6%。团队用相同提示词和工具测试了 6 个开放模型,结果与 Terminal-Bench 的相关性最高;同时发布 ORA Traces,包含 7 个模型在 5 项基准上的 3K+ 个完整轨迹。
正文
Which models are good at robot use? We ran six open models with the same prompt and tools and compared the result with public benchmarks. We found t lines up best with Terminal-Bench, where a model works in a terminal. https://t.co/8H5ida0Dsk
AI 热点