The first exam for code agents in the physical world: frozen robot tasks from many benchmark suites, each answered with a program and verified in a separate sandbox. Runs on Harbor.
Python ai-agentsbenchmarkcoding-agentsembodied-aievaluationharborllm-agentsrobot-learningroboticssimulation
Code of conduct
Embodied First Exam follows the Contributor Covenant, version 2.1. It applies in this repository (issues, pull requests, reviews) and in the project's Discord and WeChat groups.
In short: be respectful and constructive, assume good faith, and criticise work, not people. Harassment, personal attacks and discriminatory language are not accepted.
Report unacceptable behaviour to the maintainers at [email protected]. Reports are handled confidentially; the maintainers may remove comments, close threads or block participants who break this code.