ML Research Wiki / Benchmarks / Robot Manipulation / CALVIN

CALVIN

Robot Manipulation Benchmark

Performance Over Time

📊 Showing 19 results | 📏 Metric: avg. sequence length (D to D)

Top Performing Models

Rank Model Paper avg. sequence length (D to D) Date Code
1 DreamVLA DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World Knowledge 4.44 2025-07-06 📦 Zhangwenyao1/DreamVLA
2 VPP Video Prediction Policy: A Generalist Robot Policy with Predictive Visual Representations 4.29 2024-12-19 📦 roboterax/video-prediction-policy
3 RoboVLMs Towards Generalist Robot Policies: What Matters in Building Vision-Language-Action Models 4.25 2024-12-18 📦 Robot-VLAs/RoboVLMs
4 Openhelix OpenHelix: A Short Survey, Empirical Analysis, and Open-Source Dual-System VLA Model for Robotic Manipulation 4.08 2025-05-06 📦 OpenHelix-robot/OpenHelix
5 UP-VLA UP-VLA: A Unified Understanding and Prediction Model for Embodied Agent 4.08 2025-01-31 -
6 GR-MG GR-MG: Leveraging Partially Annotated Data via Multi-Modal Goal-Conditioned Policy 4.04 2024-08-26 📦 bytedance/GR-MG
7 MoDE Efficient Diffusion Transformer Policies with Mixture of Expert Denoisers for Multitask Learning 4.01 2024-12-17 📦 intuitive-robots/MoDE_Diffusion_Policy
8 RoboUniView RoboUniView: Visual-Language Model with Unified View Representation for Robotic Manipulation 3.86 2024-06-27 📦 liufanfanlff/robouniview
9 UniVLA UniVLA: Learning to Act Anywhere with Task-centric Latent Actions 3.80 2025-05-09 📦 opendrivelab/univla
10 RoboDual Towards Synergistic, Generalized, and Efficient Dual-System for Robotic Manipulation 3.66 2024-10-10 -

All Papers (19)

Zhangwenyao1/DreamVLA
roboterax/video-prediction-policy
Robot-VLAs/RoboVLMs
OpenHelix-robot/OpenHelix
bytedance/GR-MG
intuitive-robots/MoDE_Diffusion_Policy
liufanfanlff/robouniview
opendrivelab/univla
nickgkan/3d_diffuser_actor
openvla/openvla stanford-iliad/openvla-mini pie33000/OpenVLA
nickgkan/3d_diffuser_actor
bytedance/gr-1 bytedance/GR-MG GR1-Manipulation/GR-1
google-research/robotics_transformer