As of: 2026-11-13 13:49 CET.
Researched and written by AI agents (Claude Opus 5.5 in Claude Code), with a human editor. How we work: https://postcutoff.com/about/
Canonical page: https://postcutoff.com/m/atlas-large-behavior-model/

# Atlas Large Behavior Model (Boston Dynamics + TRI LBM)

Boston Dynamics, Large Behavior Models (TRI) family. Status: current. Type: robotics model. Released: 2025-08-20.

## How to call it

| Provider | Model id | Endpoint | Docs |
|---|---|---|---|
| Not available (internal research policy for Atlas) |  |  | https://bostondynamics.com/blog/large-behavior-models-atlas-find-new-footing/ |
| TRI LBM Eval (open simulation benchmark, not the model) |  |  | https://github.com/ToyotaResearchInstitute/lbm_eval |

## Pricing

- Price not published.
- Last checked: not recorded

## Specs

- Input: image, text
- Output: action
- Context window: not published
- Max output: not published
- Open weights: no
- Licence: proprietary

## Where it stands

- Newer robotics models in the registry since its release: 23. The 5 newest:
  - Praxis-1 (2026-09-30) https://postcutoff.com/m/praxis-1/
  - Helix 2.5 (2026-09-17) https://postcutoff.com/m/figure-helix-2-5/
  - UnifoLM-WLA-1.0 (2026-09-10) https://postcutoff.com/m/unifolm-wla-1-0/
  - Skild S1 (Skild Brain) (2026-08-25) https://postcutoff.com/m/skild-s1/
  - Generalist GEN-1.5 (2026-08-19) https://postcutoff.com/m/generalist-gen-1-5/
- Closed weights.

## What stands out

- One language-conditioned policy for whole-body loco-manipulation: A single end-to-end policy maps images, proprioception and language to actions for the full 50-DoF Atlas at 30 Hz, combining stepping, crouching and center-of-mass shifts with dexterous manipulation in long-horizon tasks, replacing separate walking and manipulation controllers. Source: https://bostondynamics.com/blog/large-behavior-models-atlas-find-new-footing/
- Diffusion Transformer with flow matching: 450M-parameter Diffusion Transformer trained with a flow-matching objective, predicting 48-step action chunks (1.6 s); trained on Atlas teleop data, the Atlas Manipulation Test Stand, TRI's Ramen dataset and simulation co-training. Source: https://bostondynamics.com/blog/large-behavior-models-atlas-find-new-footing/
- Inference-time speed-up: Policies can run 1.5-2x faster than the human demos at inference time without retraining by rescaling action timing. Source: https://bostondynamics.com/blog/large-behavior-models-atlas-find-new-footing/
- Pretraining cuts task data by up to 80%: TRI's LBM study (~1,700 h of robot data, 1,800 real and 47,000+ sim rollouts) found pretrained LBMs need up to 80% less task-specific data. Source: https://toyotaresearchinstitute.github.io/lbm1/

## Notes

Research collaboration announced Aug 2025 (Toyota release: https://newsroom.toyota.eu/ai-powered-robot-by-boston-dynamics-and-toyota-research-institute-takes-a-key-step-towards-general-purpose-humanoids/). The production electric Atlas (CES 2026) also integrates Google DeepMind foundation models (Gemini Robotics); Hyundai trains Atlas on parts logistics at its Georgia RMAC (2026-09-22). No public weights or API for the Atlas LBM. Exact announcement day (2025-08-20) is from press coverage dated 2025-08-20/21.


Model page: https://postcutoff.com/m/atlas-large-behavior-model/