Request access to Verne V0.5

Verne reviews each request before it gives access. Verne uses your answers to manage your license and to contact you about Verne V0.5. The Verne Privacy Notice describes how Verne processes this information.

The Verne V0.5 Model License, version 1.0, governs the use of Verne V0.5. Read the license before you request access. When you submit this form, you accept the license. For commercial use, please contact partnership@vernerobotics.com. We would love to work with you! The license does not permit use in a country or region under comprehensive US sanctions, or use by a person on a US restricted-party list.

Verne V0.5 LIBERO

Verne V0.5 is an open-weight world action model for general-purpose robotics, made by Verne. This checkpoint is V0.5 fine-tuned on the LIBERO simulation benchmark. One model covers all four LIBERO suites. It succeeds in 99.3% of 2,000 episodes.

Model details


Developed by	Verne Team
Model type	World action model (WAM): a video transformer and an action transformer, trained with flow matching
Inputs	Current camera frames, memory of past observations, robot state, and a language instruction
Output	A chunk of 32 targets at 30 Hz: tool poses, gripper openings, base poses, and progress
Instruction language	English
Fine-tuned from	vernerobotics/v0.5-base
Fine-tuning data	The LIBERO training demonstrations, all four suites
License	Verne V0.5 Model License

Results

LIBERO has four suites of ten tasks: Spatial, Object, Goal, and Long. Long is the suite of multi-step tasks.

Suite	Success	Episodes
Spatial	98.8%	494 / 500
Object	99.8%	499 / 500
Goal	99.2%	496 / 500
Long	99.2%	496 / 500
Average	99.3%	1,985 / 2,000

The 95% interval of the average is 98.8% to 99.7%. Each task ran 50 episodes.

Comparison with published results

Model	Average of 4 suites	Long
Verne V0.5	99.3%	99.2%
ABot-M0.5	99.4%	98.4%
VPP2	98.8%	98.0%
Cosmos Policy	98.5%	97.6%
X-VLA	98.1%	97.6%
Fast-WAM	97.6%	95.2%
π0.5	96.85%	92.4%
π0	94.15%	85.2%

Rows are sorted by the mean of the two columns. Other results are as published by their authors. V0.5 and π0.5 tie on the Spatial suite at 98.8%. On Long, V0.5 leads π0.5 by 6.8 points.

Checkpoints

Checkpoint	Description
v0.5-base	Pretrained base. Start here to fine-tune.
v0.5-libero	Fine-tuned on LIBERO. 99.3% average success.
v0.5-robotwin	Fine-tuned on RoboTwin 2.0. 81.0% clean, 73.4% randomized.

Model

A video transformer and an action transformer share information through masked attention. During training, they learn together with video and action flow-matching objectives. At runtime, only the action path runs. The model does not generate future video.

V0.5 trains in three stages: robot-video pretraining, joint video and action pretraining, and task post-training. The pretraining data are over 1.7 million demonstrations. See the base card for details. This checkpoint completes task post-training on LIBERO.

Uses

Intended uses

Research on robot learning.
Comparison with other models on the LIBERO benchmark.

Out of scope

Use on a physical robot. This checkpoint is tuned for the LIBERO simulator.
Any use that the license does not permit. This includes weapons, unlawful surveillance, and use in sanctioned countries and regions.

Limitations

This checkpoint is tuned for the LIBERO simulator, its robot, and its cameras. Do not expect it to work on other robots or scenes without fine-tuning.
This release contains the weights and a minimal inference package. It has no training or fine-tuning code. To fine-tune V0.5 on your own robot and tasks, sign up for the Verne fine-tuning platform at app.vernerobotics.com.

Physical safety

V0.5 outputs actions that move physical machines. A machine that moves can injure people and damage property. Before you run V0.5 on a robot, assess the risks, install an emergency stop and speed and force limits, and supervise the robot while it runs. Section 6 of the license makes you responsible for these measures.

License

The Verne V0.5 Model License governs the use of these weights. In short:

For commercial use, please contact partnership@vernerobotics.com. We would love to work with you!
Use in a country or region under comprehensive US sanctions, and use by a person on a US restricted-party list, is not permitted.
Weapons and unlawful surveillance are not permitted.

This summary is not the license. The LICENSE file controls. See NOTICE for third-party notices.

Citation

@misc{verne2026v05,
  title  = {Verne V0.5: An Open-Weight World Action Model to Accelerate Industrial Robot Deployments},
  author = {{Verne Team}},
  year   = {2026},
  url    = {https://vernerobotics.com}
}