ModelScope(@ModelScope2022):One physical intelligence loop, now in 2B and 8B. PhysBrain 1.5 is here！ 🤖 https://t.co/ejiKFrUfJW 🤖 https://t.co/eJ3wjxgPUJ 📄 https://t.co/SBjnMYqPZl 🏆 PhysBrain 1.5-8B scores 72.5 across 28 embodied-understanding benchmarks, ranking #1 among the evaluated open-source models and leading 14 tasks. The compact 2B reaches 66.6. 🧭 Both models cover spatial perception, 3D reasoning, embodied planning, grounding, affordance, and trajectory reasoning. 🦾 They generate end-effector trajectories and predict future states as aligned RGB, depth, and robot masks. 🧠 Built on Qwen3-VL, PhysBrain 1.5 models language, spatial outputs, actions, and future states as tokens within one autoregressive backbone. No task-specific heads.

ModelScope@ModelScope2022

2026.09.15 14:00

One physical intelligence loop, now in 2B and 8B. PhysBrain 1.5 is here！ 🤖 🤖 📄 🏆 PhysBrain 1.5-8B scores 72.5 across 28 embodied-understanding benchmarks, ranking #1# among the evaluated open-source models and leading 14 tasks. The compact 2B reaches 66.6. 🧭 Both models cover spatial perception, 3D reasoning, embodied planning, grounding, affordance, and trajectory reasoning. 🦾 They generate end-effector trajectories and predict future states as aligned RGB, depth, and robot masks. 🧠 Built on Qwen3-VL, PhysBrain 1.5 models language, spatial outputs, actions, and future states as tokens within one autoregressive backbone. No task-specific heads.