CALVIN

Normalizer

CALVIN — metrics, requirements, and run commands.

Last updated: Jul 11, 2026

On this page

About Metrics Task YAML Primary Environment setup Runtime environment Evaluation data Checkpoints & assets Key environment variables Verify setup Run Evaluation Set Candidate Artifacts Import Official Results Score Generated Artifacts Direct In-Tree Runner Requirements Inputs Environment Outputs

About

CALVIN external benchmark task manifest for long-horizon language-conditioned manipulation.

Metrics

CALVIN external benchmark task manifest for long-horizon language-conditioned manipulation.

Task YAML

worldfoundry/data/benchmarks/tasks/external/calvin.yaml

Primary

success_rate

Metric	Focus
`success_rate`	Share of episodes or tasks that complete successfully.
`sequence_success`	Share of episodes or tasks that complete successfully.
`task_success`	Share of episodes or tasks that complete successfully.
`completion`	Fraction of consecutive CALVIN language-conditioned sub-tasks completed without environment reset.

Environment setup

Runtime environment

Conda env: giga-world-policy-py311.
Separate setup: defaults to the unified WorldFoundry env (needs_new_env: false); a benchmark-only conda env is usually not required.
CALVIN 官方 rollout 需要数据集 split、policy checkpoint 和 long-horizon evaluator 输出；轻量 preflight 不启动仿真/评测。

Evaluation data

WorldFoundry tracks the upstream CALVIN runtime and normalizes official result files; dataset materialization is handled outside this manifest.
Candidate model outputs: set WORLDFOUNDRY_CALVIN_RESULTS_PATH to the generated-video or rollout artifact root.
${WORLDFOUNDRY_CACHE_DIR}/repos/mees--calvin

Checkpoints & assets

This benchmark is primarily rollout- or official-result-driven; see catalog requires and the task YAML for policy/simulator checkpoints.

Key environment variables

WORLDFOUNDRY_CALVIN_ROOT
WORLDFOUNDRY_CALVIN_DATASET_ROOT
WORLDFOUNDRY_CALVIN_RESULTS_PATH

Verify setup

PYTHONPATH=${WORLDFOUNDRY_CACHE_DIR}/repos/mees--calvin:src ${WORLDFOUNDRY_CONDA_ENVS_ROOT}/worldfoundry-giga-world-policy-py311/bin/python -m worldfoundry.evaluation.tasks.execution.orchestration.runtime_preflight --profile calvin --manifest worldfoundry/data/benchmarks/runtime_profiles/official/calvin.yaml --output-dir tmp/worldfoundry_preflight/calvin --json

Run Evaluation

After preparing the assets and candidate artifacts listed on this page, use the public run entry points below.

Set Candidate Artifacts

export WORLDFOUNDRY_GENERATED_ARTIFACT_DIR=/path/to/generated/artifacts

Import Official Results

worldfoundry-eval zoo benchmark-run \
  --benchmark-id calvin \
  --mode normalizer \
  --official-results-path /path/to/official/results-or-report \
  --generated-artifact-dir "${WORLDFOUNDRY_GENERATED_ARTIFACT_DIR}" \
  --output-dir tmp/calvin/normalizer \
  --json

Score Generated Artifacts

worldfoundry-eval zoo benchmark-run \
  --benchmark-id calvin \
  --mode official-run \
  --generated-artifact-dir "${WORLDFOUNDRY_GENERATED_ARTIFACT_DIR}" \
  --output-dir tmp/calvin/official-run \
  --json

Direct In-Tree Runner

worldfoundry-eval zoo benchmark-run --benchmark-id calvin --mode official-validation --official-results-path <official_results.json> --output-dir <out> --json