Evaluate a benchmark task (delegates to benchmark instance).
(self, name: str, task: Task)
| 488 | return await instance.step() |
| 489 | |
| 490 | async def eval(self, name: str, task: Task) -> Optional[Task]: |
| 491 | """Evaluate a benchmark task (delegates to benchmark instance).""" |
| 492 | instance = await self.get(name) |
| 493 | if instance is None: |
| 494 | raise ValueError(f"Benchmark '{name}' not found") |
| 495 | return await instance.eval(task) |
| 496 | |
| 497 | async def stats(self, name: str) -> Optional[Stats]: |
| 498 | """Get benchmark statistics (delegates to benchmark instance).""" |