Claude Fable 5.2 登顶 LIBERO-10 机器人控制榜,成功率 44%→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.
「具身」频道最新
- VITURE 推 599 美元 Phantom Beast XR 眼镜,为影刃零定制 174 英寸巨幕 — Scobleizer · 2026-11-18
- StarVLA 开源:乐高式 VLA 开发框架已获近 4000 GitHub 星 — wzenus · 2026-11-18
- 可对着耳语的 AI 戒指 museo 下月发货,开放自建应用与 Agent 工作流 — Scobleizer · 2026-11-18
- 强化学习让 5 吨滑移装载机学会双轮平衡等特技 — Scobleizer · 2026-11-18
- Scale AI 开源 1700 小时双臂机器人数据集,子任务标签实现跨机器人迁移 — yacinelearning · 2026-11-18
- a16z 领投 1700 万美元,Valkryn 要做自主作战的「实战检验实验室」 — espricewright · 2026-11-18