The proving ground for physical AI.
π€ Explore rollout data Β· π Leaderboard Β· π Website Β· π Paper Β· π» GitHub
**RoboColosseum evaluates robot policies in the real world, at scale.** We measure how reliably models work across everyday environments, tasks, and robot embodiments. - π€ **100+ robots**, including SO-101, Franka, bimanual YAM, and Unitree G1 - π **140+ real-world scenes** with thousands of tasks - π **10,000 free evaluation hours** in a shared pool for academic labs ## π€ Open rollout data **Our commitment: every evaluation rollout, openly released on Hugging Faceβfailures included.** Explore robot attempts in the [datasets below](https://huggingface.co/RoboColosseum#datasets) to understand policy behavior and failures. Each dataset card explains its contents, evaluation setup, and usage details. ## π€οΈ Two evaluation tracks **Open track.** Blind, head-to-head tests measure how well models handle new tasks in real-world environments, with no task-specific training. **Fine-tune track.** Models learn from the same fixed, open-source dataset, then undergo evaluation to measure how well they adapt to the task. ## π Free evaluations for academia Need evaluations beyond what your lab can run? [Apply for a share of 10,000 free evaluation hours β](https://app.youform.com/forms/riubycrq)