Embodied-agent benchmarks
Embodied-agent benchmarks covers standard tasks and leaderboards for evaluating robot policies and embodied agents.
In brief
Embodied-agent benchmarks, in brief.
What it isEmbodied-agent benchmarks covers standard tasks and leaderboards for evaluating robot policies and embodied agents.
Where it sitsOne of 14 categories in the Robotics and physical AI layer. Robotics and physical AI covers the software and hardware used to build AI that moves in the real world: robot models, simulators, drone and driving stacks, robot platforms with developer kits, and the data they learn from.
What we track25 products, including AI2-THOR / ProcTHOR, ALFRED, BEHAVIOR-1K / BEHAVIOR Challenge, CALVIN and CARLA Autonomous Driving Leaderboard.
The products
25 products in Embodied-agent benchmarks.
Each name opens a search for that product in our index.
ProductMakerIts own site
From our census of 2026-11-08. A product listed here is one that belongs in this category; the search answer says whether we have checked it.
Questions
Embodied-agent benchmarks, answered.
What is Embodied-agent benchmarks in AI infrastructure?Embodied-agent benchmarks covers standard tasks and leaderboards for evaluating robot policies and embodied agents.
Which layer of AI infrastructure is Embodied-agent benchmarks in?Embodied-agent benchmarks is in the Robotics and physical AI layer. Robotics and physical AI covers the software and hardware used to build AI that moves in the real world: robot models, simulators, drone and driving stacks, robot platforms with developer kits, and the data they learn from.
Which products are in Embodied-agent benchmarks?We track 25 products in Embodied-agent benchmarks, including AI2-THOR / ProcTHOR, ALFRED, BEHAVIOR-1K / BEHAVIOR Challenge, CALVIN, CARLA Autonomous Driving Leaderboard, EmbodiedBench, Habitat (Habitat Challenge) and HumanoidBench. The full list is on this page.
Robotics and physical AI
The other categories in Robotics and physical AI.
Autonomous driving software stacksDrone stacksHumanoid & robot platforms with SDKsLLM-to-robot interfaces & robot agentsROS ecosystemRobot cloud & fleet managementRobot foundation modelsRobot hardware dev kits & computeRobot learning datasetsRobot perception, SLAM & motion planning librariesRobotics data logging & visualizationSimulationTeleop / robot data collection