D
For DockerAI Platform

Docker Build Cloud

Docker (Engine, Hub, Build Cloud, Scout, Desktop, Model Runner) · Docker

Container Platform — Docker

Docker evals — Docker Build Cloud (relift v3 InfraRed)

About Docker

Docker is the container platform — Docker Engine, Docker Desktop, Docker Hub registry, Docker Build Cloud for managed cloud builders, Docker Scout for image vulnerability scanning and supply-chain policy, Docker Compose for multi-container dev, and Docker Model Runner for local LLM inference. Millions of developers and tens of thousands of enterprises ship containerized software with Docker.

Employees

~600

Industry

Developer Infrastructure

Headquarters

Palo Alto, CA

Sample tests· showing 3 of 9

#InputExpected behaviorCheck
01

Operator wants Docker Build Cloud builds from CI. CI currently uses the default 'docker' driver which only builds for the runner's architecture.

Run 'docker buildx create --driver cloud <org>/<builder-name> --use'. Subsequent 'docker buildx build' streams the build to the cloud builder endpoint; native ARM and amd64 stages run on dedicated hardware (no QEMU). Authenticate to Docker Hub first (docker login).

Pass / FailAi Platformhigh
02

Team builds Python+native-deps images for both linux/amd64 and linux/arm64. Local QEMU build for ARM takes 12 min; native ARM stage from CI ~2 min.

Run 'docker buildx build --builder <cloud> --platform linux/amd64,linux/arm64 --push'. Build Cloud executes amd64 stages on amd64 hosts and arm64 stages on arm64 hosts — no emulation. Net speedup is workload-dependent [REQUIRES-VERIFICATION on the 6x figure].

Pass / FailAi Platformmedium
03

Developer A and developer B run the same build with identical deps. A's build is cold; B (later) gets a cache hit by sharing the cloud builder.

Build Cloud maintains per-builder cache shared across all users of that builder. Both A and B target the same <org>/<builder>; B's overlapping layers are imported from cache. Verify in build output (CACHED lines). Cache eviction policy is provider-managed.

Pass / FailAi Platformmedium

How this eval is graded

Grade against expected.ideal_behavior and expected.rubric. Per-criterion pass requires mean >= 4.0 and no criterion below 3.

Rubric criteria

  • Docker
  • Ai Platform
  • Docker Build Cloud

Recommended for

Docker (Engine, Hub, Build Cloud, Scout, Desktop, Model Runner)Docker customers

Works with

Related evals

Run this eval in your workspace

Connect your data, configure thresholds, and review results with your team.