We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
1 parent 92cd591 commit fe39fd8Copy full SHA for fe39fd8
eval_protocol/benchmarks/test_frozen_lake.py
@@ -46,7 +46,7 @@ def frozen_lake_to_evaluation_row(data: List[Dict[str, Any]]) -> List[Evaluation
46
num_runs=1,
47
max_concurrent_rollouts=3,
48
mode="pointwise",
49
- server_script_path="examples/frozen_lake_mcp/server.py",
+ server_script_path="eval_protocol/mcp_servers/frozen_lake/server.py",
50
)
51
def test_frozen_lake_evaluation(row: EvaluationRow) -> EvaluationRow:
52
"""
0 commit comments