Model comparison · robotics
GR00T N1.7 3B vs OpenVLA 7B
Symmetrical, primary-source facts with unknown values left visible. No winner is assigned without comparable measurements.
FieldAt a glance
NVIDIA · activeGR00T N1.7 3BVerified Aug 28, 2026
OpenVLA Research Team · activeOpenVLA 7BVerified Aug 28, 2026
Technical differences
Side-by-side facts
| Field | GR00T N1.7 3B | OpenVLA 7B |
|---|---|---|
| Developer | NVIDIA | OpenVLA Research Team |
| Family | Isaac GR00T | OpenVLA |
| Model | GR00T N1.7 3B | OpenVLA 7B |
| Version | N1.7 | 7B |
| Lifecycle | active | active |
| Input modalities | Text, Image, Robot state | Text, Image, Robot state |
| Output modalities | Robot action | Robot action |
| Context window | Unknown | Unknown |
| Total parameters | 3000000000 | 7000000000 |
| Active parameters | Unknown | Unknown |
| License | apache-2.0 | Unknown |
| Open weights | Yes | Yes |
| API available | No | No |
| Self-hostable | Yes | Yes |
| Capabilities | cross-embodiment, dexterous-manipulation, whole-body-control, fine-tuning | cross-embodiment, fine-tuning, generalist-manipulation |
| Robotics model type | Vision-language-action model | Vision-language-action model |
| Action representation | Predictive chunks of relative joint motions | Tokenized actions decoded to continuous robot controls |
| Control architecture | Vision-language backbone with action expert | Fused SigLIP and DINOv2 visual encoder with Llama 2 7B backbone |
| Inference location | On device | Flexible |
| Native control rate (Hz) | Unknown | Unknown |
| Supported embodiments | Unitree G1, AgiBot Genie-1, Fourier GR-1, bimanual manipulation platforms | WidowX, Google Robot, Franka Panda |
| Training data | Mixture of real teleoperation, synthetic robot data, and internet-scale video described by NVIDIA. | 970,000 robot manipulation trajectories from Open X-Embodiment described by the authors. |
18 comparable fields · 11 material differences · Pair passes the primary-source comparison gate
Primary benchmark evidence
Comparable performance
No protocol-matched benchmark yet.Results appear here only when both models share the same benchmark version, metric, evaluation protocol, and evidence class.
GR00T N1.7 3B capabilities
Input price—
Output price—
Serving providers0
Canonical IDnvidia/GR00T-N1.7-3B
OpenVLA 7B capabilities
Input price—
Output price—
Serving providers0
Canonical IDopenvla/openvla-7b
Internal comparison graph
Related comparisons
Primary evidence