# LIBERO-Para (/docs/evaluation/benchmark-hub/libero-para)



## About [#about]

LIBERO-Paraphrase tests whether VLA policies generalize when task language is paraphrased.

## Metrics [#metrics]

LIBERO-Para external benchmark task manifest for paraphrased language-conditioned robot manipulation evaluation.

### Task YAML [#task-yaml]

`worldfoundry/data/benchmarks/tasks/external/libero-para.yaml`

### Primary [#primary]

* `success_rate`

| Metric                            | Focus                                                                                          |
| --------------------------------- | ---------------------------------------------------------------------------------------------- |
| `success_rate`                    | Share of episodes or tasks that complete successfully.                                         |
| `paraphrase_success_rate`         | Share of episodes or tasks that complete successfully.                                         |
| `language_generalization_success` | Share of episodes or tasks that complete successfully.                                         |
| `task_success`                    | Share of episodes or tasks that complete successfully.                                         |
| `action_accuracy`                 | Correctness of predicted actions, states, or outcomes against the benchmark success criterion. |

## Environment setup [#environment-setup]

### Runtime environment [#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.
* LIBERO-Para is tracked as an embodied benchmark, not a model runner; WorldFoundry normalizes official-shaped result exports only.
* Full official status requires the cau-hai-lab/LIBERO-Para runtime, HAI-Lab/LIBERO-Para data, policy checkpoint, and paraphrase split mapping.

### Evaluation data [#evaluation-data]

* Candidate model outputs: set `WORLDFOUNDRY_LIBERO_PARA_RESULTS_PATH` to the generated-video or rollout artifact root.
* `${WORLDFOUNDRY_HFD_DATASET_ROOT}/HAI-Lab__LIBERO-Para`
* `${WORLDFOUNDRY_CACHE_DIR}/repos/cau-hai-lab--LIBERO-Para`

### Checkpoints & assets [#checkpoints--assets]

* Base-model / metric dependencies: `libero_para_source_assets`, `libero_para_dataset_assets`.
* Default metric-checkpoint paths and override env vars are listed in the [local assets guide](/docs/guides/local-assets).

### Key environment variables [#key-environment-variables]

* `WORLDFOUNDRY_LIBERO_PARA_ROOT`
* `WORLDFOUNDRY_LIBERO_PARA_RESULTS_PATH`
* `WORLDFOUNDRY_LIBERO_PARA_DATASET_ROOT`

### Verify setup [#verify-setup]

```bash
PYTHONPATH=${WORLDFOUNDRY_CACHE_DIR}/repos/cau-hai-lab--LIBERO-Para:src ${WORLDFOUNDRY_CONDA_ENVS_ROOT}/worldfoundry-giga-world-policy-py311/bin/python -m worldfoundry.evaluation.tasks.execution.orchestration.runtime_preflight --profile libero-para --manifest worldfoundry/data/benchmarks/runtime_profiles/official/libero-para.yaml --output-dir tmp/worldfoundry_preflight/libero-para --json
```

## Run Evaluation [#run-evaluation]

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

### Set Candidate Artifacts [#set-candidate-artifacts]

```bash
export WORLDFOUNDRY_GENERATED_ARTIFACT_DIR=/path/to/generated/artifacts
```

### Import Official Results [#import-official-results]

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

### Score Generated Artifacts [#score-generated-artifacts]

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

### Direct In-Tree Runner [#direct-in-tree-runner]

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

## Requirements [#requirements]

### Inputs [#inputs]

* Official LIBERO-Para repository checkout
* HAI-Lab/LIBERO-Para dataset root
* Policy checkpoint for selected upstream eval script
* Official result dump from metrics/analyze\_results.py or equivalent structured export

### Environment [#environment]

* `WORLDFOUNDRY_LIBERO_PARA_RESULTS_PATH`

### Outputs [#outputs]

* `scorecard.json`
* `benchmark_contract.json`
* `raw_metric_table.jsonl`
* `raw_results.jsonl`

[← Benchmark Hub](/docs/evaluation/benchmark-hub)