diff --git a/src/crewai/crew.py b/src/crewai/crew.py
index f36df2a03..55981fb64 100644
--- a/src/crewai/crew.py
+++ b/src/crewai/crew.py
@@ -1125,19 +1125,20 @@ class Crew(BaseModel):
     def test(
         self,
         n_iterations: int,
-        openai_model_name: Optional[str] = None,
+        eval_llm: Union[str, InstanceOf[LLM], Any] = Field(description="Language model that will run the agent.", default=None),
         inputs: Optional[Dict[str, Any]] = None,
     ) -> None:
         """Test and evaluate the Crew with the given inputs for n iterations concurrently using concurrent.futures."""
         test_crew = self.copy()
+        eval_llm = create_llm(eval_llm)
 
         self._test_execution_span = test_crew._telemetry.test_execution_span(
             test_crew,
             n_iterations,
             inputs,
-            openai_model_name,  # type: ignore[arg-type]
+            eval_llm.model,  # type: ignore[arg-type]
         )  # type: ignore[arg-type]
-        evaluator = CrewEvaluator(test_crew, openai_model_name)  # type: ignore[arg-type]
+        evaluator = CrewEvaluator(test_crew, eval_llm)  # type: ignore[arg-type]
 
         for i in range(1, n_iterations + 1):
             evaluator.set_iteration(i)
diff --git a/src/crewai/utilities/evaluators/crew_evaluator_handler.py b/src/crewai/utilities/evaluators/crew_evaluator_handler.py
index ef9b908e1..1393cdf56 100644
--- a/src/crewai/utilities/evaluators/crew_evaluator_handler.py
+++ b/src/crewai/utilities/evaluators/crew_evaluator_handler.py
@@ -1,6 +1,6 @@
 from collections import defaultdict
 
-from pydantic import BaseModel, Field
+from pydantic import BaseModel, Field, InstanceOf
 from rich.box import HEAVY_EDGE
 from rich.console import Console
 from rich.table import Table
@@ -9,6 +9,7 @@ from crewai.agent import Agent
 from crewai.task import Task
 from crewai.tasks.task_output import TaskOutput
 from crewai.telemetry import Telemetry
+from crewai.llm import LLM
 
 
 class TaskEvaluationPydanticOutput(BaseModel):
@@ -32,9 +33,9 @@ class CrewEvaluator:
     run_execution_times: defaultdict = defaultdict(list)
     iteration: int = 0
 
-    def __init__(self, crew, openai_model_name: str):
+    def __init__(self, crew, eval_llm: InstanceOf[LLM]):
         self.crew = crew
-        self.openai_model_name = openai_model_name
+        self.llm = eval_llm
         self._telemetry = Telemetry()
         self._setup_for_evaluating()
 
@@ -51,7 +52,7 @@ class CrewEvaluator:
             ),
             backstory="Evaluator agent for crew evaluation with precise capabilities to evaluate the performance of the agents in the crew based on the tasks they have performed",
             verbose=False,
-            llm=self.openai_model_name,
+            llm=self.llm,
         )
 
     def _evaluation_task(
@@ -181,7 +182,7 @@ class CrewEvaluator:
                 self.crew,
                 evaluation_result.pydantic.quality,
                 current_task.execution_duration,
-                self.openai_model_name,
+                self.llm.model,
             )
             self.tasks_scores[self.iteration].append(evaluation_result.pydantic.quality)
             self.run_execution_times[self.iteration].append(