First humanoid eval results: Unitree G1 completes 0 of 625 fine-tuned trials
DJiafei · x · 2026-11-05
Playground adds RoboColosseum to its Robot Intelligence Index, bringing the first real-humanoid eval results. After fine-tuning, SO-101 completes 59%, YAM 54%, Franka 49% — while the Unitree G1 humanoid completes 0 of 625 trials, exposing a stark embodiment gap.
Related event: Unitree G1 Becomes Primary Platform for RoboColosseum Humanoid Benchmark(2 posts)→
More from Embodied
- NYU and Meta FAIR introduce ID-WM, a hierarchical world model beating baselines by 38.5% — ylecun · 2026-11-05
- mjorbit: open-source space robotics simulator runs thousands of parallel worlds on one GPU — ChongZzZhang · 2026-11-05
- Centauro-style robot with humanoid torso and wheeled legs goes viral — chrisalbon · 2026-11-05
- Scoble to bring a rentable booth robot to CES after seeing the stunt work thousands of times — Scobleizer · 2026-11-05
- USC paper shows VLAs can keep the same rationale while adversarial perturbations change their actions — USC · 2026-11-05
- 11,398 real-world evals: GPT-6 Astra stands out in 5-VLA policy comparison — DJiafei · 2026-11-05