{
 "schema_version": 1,
 "generated": "2026-10-26",
 "repo": "mll-lab-nu/embodied-first-exam",
 "name": "embodied-first-exam",
 "owner": "mll-lab-nu",
 "slug": "mll-lab-nu-embodied-first-exam",
 "github": "https://github.com/mll-lab-nu/embodied-first-exam",
 "what": "A benchmark called Embodied First Exam that tests code agents on frozen robot tasks, where each answer is a program run and verified in a separate sandbox, built to run on Harbor.",
 "why": "178 stars, launched 38 days ago",
 "language": "Python",
 "requirements": [
  "Linux x86_64 host with git, uv, and Docker Engine with Compose v2 and BuildKit (or rootless podman with -e podman)",
  "NVIDIA driver and NVIDIA Container Toolkit for any GPU task",
  "An API key for the agent's model in .env, or a ChatGPT or Claude subscription",
  "Enough free disk for the benchmark images (1 to 150 GB depending on the suite)"
 ],
 "audience_note": "Robotics and AI researchers, and teams building coding agents, who need to measure how well an agent writes code that controls robots.",
 "risk": "none",
 "section": "earlier",
 "weekly_rank": null,
 "category": "Research",
 "url": "https://dedupedai.com/use-cases/mll-lab-nu-embodied-first-exam/",
 "use_case_count": 4,
 "use_cases": [
  {
   "id": "mll-lab-nu-embodied-first-exam--run-core-exam-with-coding-agent",
   "title": "Run the core exam with a coding agent",
   "best": true,
   "url": "https://dedupedai.com/use-cases/mll-lab-nu-embodied-first-exam/run-core-exam-with-coding-agent/",
   "json": "https://dedupedai.com/use-cases/u/mll-lab-nu-embodied-first-exam/run-core-exam-with-coding-agent.json"
  },
  {
   "id": "mll-lab-nu-embodied-first-exam--test-one-benchmark-suite",
   "title": "Test one benchmark suite with a single command",
   "best": false,
   "url": "https://dedupedai.com/use-cases/mll-lab-nu-embodied-first-exam/test-one-benchmark-suite/",
   "json": "https://dedupedai.com/use-cases/u/mll-lab-nu-embodied-first-exam/test-one-benchmark-suite.json"
  },
  {
   "id": "mll-lab-nu-embodied-first-exam--run-exam-on-subscription-login",
   "title": "Run the exam on a ChatGPT or Claude subscription",
   "best": false,
   "url": "https://dedupedai.com/use-cases/mll-lab-nu-embodied-first-exam/run-exam-on-subscription-login/",
   "json": "https://dedupedai.com/use-cases/u/mll-lab-nu-embodied-first-exam/run-exam-on-subscription-login.json"
  },
  {
   "id": "mll-lab-nu-embodied-first-exam--test-safety-suite-without-gpu",
   "title": "Test an agent on the Embodied Safety Exam without a GPU",
   "best": false,
   "url": "https://dedupedai.com/use-cases/mll-lab-nu-embodied-first-exam/test-safety-suite-without-gpu/",
   "json": "https://dedupedai.com/use-cases/u/mll-lab-nu-embodied-first-exam/test-safety-suite-without-gpu.json"
  }
 ],
 "disclaimer": "Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk."
}