← Leaderboard
GR00T 2
World-actionNVIDIA · Nov 9, 2026
World-action model that denoises future video and actions together with one 2B transformer, pretrained on about 400k hours of egocentric human video, 10k hours of UMI data and 23.5k hours of teleoperation; a lighter GR00T 2 Turbo runs on the G1’s Jetson Thor. Its whitepaper self-reports 67.2% on RoboCasa365, 35.5% on RoboDojo and 47.4% on RoboLab, none yet on the official boards; code is announced for December 2026.
- Type
- World-action
- Parameters
- 2B
- Backbone
- Cosmos-Predict2.5-2B video diffusion transformer
- Weights
- Unknown
- License
- –
- Commercial use
- Unclear
- Released
- Nov 9, 2026
- Robots
- YAM, DROID Franka, Tianji + Sharpa hands (Dexter), Wuji hands, Unitree G1
- SO-101
- –
- LeRobot
- –
- Inputs
- RGB · P · L
- VRAM
- –
Benchmark results
3 of 13 benchmarksRoboLab-120Simulation
- Paper / model card ↗Nov 2026· self-reported· n = 1200
Success by difficulty
Simple45.6%Moderate54.6%Complex37.6%
#5 of 2347.4%, self-reported by the authors, not a leaderboard entry
RoboCasa365Simulation
- Paper / model card ↗Nov 2026· self-reported
#2 of 2767.2%, self-reported by the authors, not a leaderboard entry
RoboDojo (sim)Simulation
- Paper / model card ↗Nov 2026· self-reported· n = 6300
#9 of 5435.5%, self-reported by the authors, not a leaderboard entry
Not reported on 10 benchmarks
Wrong or missing number? Report an error