Ai2 says its MolmoAct 2 robot policy ranks first in Datapoint AI's human-preference rankings for real-world manipulation, including candy sorting and cup stacking. Datapoint AI's 55k-entry dataset and rankings of nine robot policies are free and open.
Another benchmark, another #1 for MolmoAct 2! 🤖🏆
Our robot policy tops @datapointai’s human-preference rankings for real-world manipulation tasks, including candy sorting & cup stacking.
Thanks to the Datapoint AI team for the evaluation & open dataset!
the full dataset is free and open: https://huggingface.co/datasets/datapointai/robot-policy-human-preferences-55k overall and category-wise rankings of 9 robot policies are available on our robot bench: https://trydatapoint.com/benchmark/leaderboard?track_id=btrk_0796367e510c&category_id=btrk_d57b6270f4f8
Source: Ai2 · x.comPublished
