Method eval

src/benchmark/server.py:83–85

Evaluate a benchmark task.

(self, name: str, task: Task)

        return await self.benchmark_context_manager.step(name)

    async def eval(self, name: str, task: Task) -> Optional[Task]:
        """Evaluate a benchmark task."""
        return await self.benchmark_context_manager.eval(name, task)

    async def stats(self, name: str) -> Optional[Stats]:
        """Get benchmark statistics."""