Claude Fable 5.2 tops LIBERO-10 LLM robot control benchmark, lifting success to 54%
YuXiang_IRVL · x · 2026-11-18
Claude Fable 5.2 (high reasoning) takes #1 on the LIBERO-10 benchmark for LLM robot control, beating GPT-6 Astra and Gemini 4 Argon.
- Best success rate jumps from GPT-6 Astra's 44% to 54%, zero-shot with no task-specific training
- Setup: no coding agents or tooling—LLMs directly output end-effector poses to control the robot, testing raw reasoning and action ability
- 2,100 rollout videos from GPT, Gemini and Claude models are public on the site
A notable data point that frontier LLM reasoning can transfer directly to robot action output.
More from Embodied
- VITURE launches $599 Phantom Beast XR glasses co-branded with Phantom Blade Zero — Scobleizer · 2026-11-18
- Hiking with Meta Ray-Ban Display: live map, distance and pace in view — stspanho · 2026-11-18
- StarVLA open-sources a Lego-like codebase for VLA models, nearing 4,000 GitHub stars — wzenus · 2026-11-18
- Museo, a whisperable AI ring for phone-free walks, ships next month with open dev platform — Scobleizer · 2026-11-18
- RL-trained 5-tonne skid-steer loader balances on two wheels after sim training — Scobleizer · 2026-11-18
- Scale AI's FineART: 1,700-Hour Dual-Arm Robot Dataset Where Human Subtask Labels Enable Cross-Robot Transfer — yacinelearning · 2026-11-18