UI-TARS achieved state-of-the-art results across a variety of standard benchmarks and demonstrated improvements over prior models[1]. In the OSWorld benchmark, UI-TARS achieves scores of 24.6 with 50 steps and 22.7 with 15 steps, outperforming Claude’s 22.0 and 14.9 respectively[2].
UI-TARS-72B with a 15-step budget (22.7) is comparable to Claude when the latter is given a 50-step budget (22.0), showing great execution efficiency[2]. UI-TARS-72B-DPO achieves a new SOTA result 24.6 on OSWorld with a budget of 50 steps[2].
Sign Up To Try Advanced Features
Get more accurate answers with Super Search, upload files, personalized discovery feed, save searches and contribute to the PandiPedia.
Sorry, Pandi could not find an answer.
Let's look at alternatives:
- Modify the query.
- Start a new thread.
- Remove sources (if manually added).
- Request a manual search from our human research team.