> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.nvidia.com/nemo/gym/llms.txt.
> For full documentation content, see https://docs.nvidia.com/nemo/gym/llms-full.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.nvidia.com/nemo/gym/_mcp/server.

# nemo_gym.benchmarks

Benchmark discovery and preparation utilities.

## Module Contents

### Classes

| Name                                                                    | Description                                                          |
| ----------------------------------------------------------------------- | -------------------------------------------------------------------- |
| [`BenchmarkConfig`](#nemo_gym-benchmarks-BenchmarkConfig)               | -                                                                    |
| [`PrepareBenchmarkConfig`](#nemo_gym-benchmarks-PrepareBenchmarkConfig) | Prepare benchmark data by running the benchmark's prepare.py script. |

### Functions

| Name                                                                                            | Description                             |
| ----------------------------------------------------------------------------------------------- | --------------------------------------- |
| [`_load_benchmarks_from_config_paths`](#nemo_gym-benchmarks-_load_benchmarks_from_config_paths) | -                                       |
| [`_multiprocess_benchmark_prepare_fn`](#nemo_gym-benchmarks-_multiprocess_benchmark_prepare_fn) | -                                       |
| [`list_benchmarks`](#nemo_gym-benchmarks-list_benchmarks)                                       | CLI command: list available benchmarks. |
| [`prepare_benchmark`](#nemo_gym-benchmarks-prepare_benchmark)                                   | CLI command: prepare benchmark data.    |

### Data

[`BENCHMARKS_DIR`](#nemo_gym-benchmarks-BENCHMARKS_DIR)

### API

```python
class nemo_gym.benchmarks.BenchmarkConfig()
```

**Bases:** `BaseModel`

```python
nemo_gym.benchmarks.BenchmarkConfig.from_config_path(
    config_path: pathlib.Path
) -> typing.Optional[nemo_gym.benchmarks.BenchmarkConfig]
```

classmethod

```python
nemo_gym.benchmarks.BenchmarkConfig.from_initial_config_dict(
    path: pathlib.Path,
    initial_config_dict: omegaconf.DictConfig
) -> typing.Optional[nemo_gym.benchmarks.BenchmarkConfig]
```

classmethod

```python
class nemo_gym.benchmarks.PrepareBenchmarkConfig()
```

**Bases:** [BaseNeMoGymCLIConfig](/nemo-gym/nemo_gym/config_types#nemo_gym-config_types-BaseNeMoGymCLIConfig)

Prepare benchmark data by running the benchmark's prepare.py script.

The benchmark is identified from a config\_paths entry pointing to a
benchmarks/\*/config.yaml file.

Examples:

```python
ng_prepare_benchmark "+config_paths=[benchmarks/aime24/config.yaml]"
```

```python
nemo_gym.benchmarks._load_benchmarks_from_config_paths(
    config_paths: typing.List[pathlib.Path]
) -> typing.Dict[str, nemo_gym.benchmarks.BenchmarkConfig]
```

```python
nemo_gym.benchmarks._multiprocess_benchmark_prepare_fn(
    args
)
```

```python
nemo_gym.benchmarks.list_benchmarks() -> None
```

CLI command: list available benchmarks.

```python
nemo_gym.benchmarks.prepare_benchmark() -> None
```

CLI command: prepare benchmark data.

```python
nemo_gym.benchmarks.BENCHMARKS_DIR = PARENT_DIR / 'benchmarks'
```