MCPcopy Create free account
hub / github.com/SkyworkAI/DeepResearchAgent / eval

Method eval

src/benchmark/types.py:95–97  ·  view source on GitHub ↗

Public interface for single task evaluation.

(self, task: Task)

Source from the content-addressed store, hash-verified

93 raise NotImplementedError
94
95 async def eval(self, task: Task) -> Optional[Task]:
96 """Public interface for single task evaluation."""
97 raise NotImplementedError
98
99 async def stats(self) -> Optional[Stats]:
100 """Calculate current overall statistics."""

Callers 6

test_math_benchmarkFunction · 0.45
process_single_taskFunction · 0.45
eval_without_recordingFunction · 0.45
process_single_taskFunction · 0.45
process_single_taskFunction · 0.45

Calls

no outgoing calls

Tested by 1

test_math_benchmarkFunction · 0.36