GPT-6.2 Astra tops robot-code test: 2.5B net solving 79% of LIBERO, Python code hits 96.8%
burny_tech · x · 2026-11-18
The Playground team reports GPT-6.2 Astra is the strongest robot-code author they've tested: with no simulator, demos, or web access, it wrote a 2.5B-parameter neural net solving 79% of 500 LIBERO trials, and Python code that solved 96.8% — beating Fable 5.2 (89.2%) and GPT-6 Astra (33.2%). The generational gap in LLM-generated robot control code is striking.
More from Embodied
- ImpedanceMimic learns per-joint impedance as action space, beating PHC and SimPoE on force-accurate motion imitation — tweetsatpreet · 2026-11-18
- Google building new robotics model Astra with 1M-token context, config leaks — lyraxana · 2026-11-18
- Bittensor subnet's zels decision model 'Jev' integrated into Even Realities glasses — markjeffrey · 2026-11-18
- Zhejiang & Unitree open-source Movens-5M: 5M sim-verified robot motions from web video — 机器之心 · 2026-11-18
- Waymo Temporarily Pulls Its Robotaxis From All U.S. Freeways — mikeocool · 2026-11-18
- EXOperation: a wearable robot hand makes human demos for robot learning intuitive and replayable — ybisk · 2026-11-18