diff --git a/ax/benchmark/benchmark_problem.py b/ax/benchmark/benchmark_problem.py
index 17e118446d2..234fe69a154 100644
--- a/ax/benchmark/benchmark_problem.py
+++ b/ax/benchmark/benchmark_problem.py
@@ -13,10 +13,7 @@
 
 from ax.benchmark.benchmark_metric import BenchmarkMetric
 from ax.benchmark.runners.base import BenchmarkRunner
-from ax.benchmark.runners.botorch_test import (
-    BoTorchTestProblem,
-    ParamBasedTestProblemRunner,
-)
+from ax.benchmark.runners.botorch_test import BoTorchTestProblem
 from ax.core.data import Data
 from ax.core.experiment import Experiment
 from ax.core.objective import MultiObjective, Objective
@@ -380,7 +377,7 @@ def create_problem_from_botorch(
         name=name,
         search_space=search_space,
         optimization_config=optimization_config,
-        runner=ParamBasedTestProblemRunner(
+        runner=BenchmarkRunner(
             test_problem=BoTorchTestProblem(botorch_problem=test_problem),
             outcome_names=outcome_names,
             search_space_digest=extract_search_space_digest(
diff --git a/ax/benchmark/problems/hpo/torchvision.py b/ax/benchmark/problems/hpo/torchvision.py
index 1a6e424a5f2..3f7f7008537 100644
--- a/ax/benchmark/problems/hpo/torchvision.py
+++ b/ax/benchmark/problems/hpo/torchvision.py
@@ -14,10 +14,8 @@
     BenchmarkProblem,
     get_soo_config_and_outcome_names,
 )
-from ax.benchmark.runners.botorch_test import (
-    ParamBasedTestProblem,
-    ParamBasedTestProblemRunner,
-)
+from ax.benchmark.runners.base import BenchmarkRunner
+from ax.benchmark.runners.botorch_test import ParamBasedTestProblem
 from ax.core.parameter import ParameterType, RangeParameter
 from ax.core.search_space import SearchSpace
 from ax.exceptions.core import UserInputError
@@ -216,7 +214,7 @@ def get_pytorch_cnn_torchvision_benchmark_problem(
         observe_noise_sd=False,
         objective_name="accuracy",
     )
-    runner = ParamBasedTestProblemRunner(
+    runner = BenchmarkRunner(
         test_problem=PyTorchCNNTorchvisionParamBasedProblem(name=name),
         outcome_names=outcome_names,
     )
diff --git a/ax/benchmark/problems/synthetic/discretized/mixed_integer.py b/ax/benchmark/problems/synthetic/discretized/mixed_integer.py
index 36359e9076e..b3d66ef062b 100644
--- a/ax/benchmark/problems/synthetic/discretized/mixed_integer.py
+++ b/ax/benchmark/problems/synthetic/discretized/mixed_integer.py
@@ -21,10 +21,8 @@
 from ax.benchmark.benchmark_metric import BenchmarkMetric
 
 from ax.benchmark.benchmark_problem import BenchmarkProblem
-from ax.benchmark.runners.botorch_test import (
-    BoTorchTestProblem,
-    ParamBasedTestProblemRunner,
-)
+from ax.benchmark.runners.base import BenchmarkRunner
+from ax.benchmark.runners.botorch_test import BoTorchTestProblem
 from ax.core.objective import Objective
 from ax.core.optimization_config import OptimizationConfig
 from ax.core.parameter import ParameterType, RangeParameter
@@ -104,7 +102,7 @@ def _get_problem_from_common_inputs(
         test_problem = test_problem_class(dim=dim)
     else:
         test_problem = test_problem_class(dim=dim, bounds=test_problem_bounds)
-    runner = ParamBasedTestProblemRunner(
+    runner = BenchmarkRunner(
         test_problem=BoTorchTestProblem(
             botorch_problem=test_problem, modified_bounds=bounds
         ),
diff --git a/ax/benchmark/problems/synthetic/hss/jenatton.py b/ax/benchmark/problems/synthetic/hss/jenatton.py
index fc2b40e6698..69cd824759d 100644
--- a/ax/benchmark/problems/synthetic/hss/jenatton.py
+++ b/ax/benchmark/problems/synthetic/hss/jenatton.py
@@ -11,10 +11,8 @@
 import torch
 from ax.benchmark.benchmark_metric import BenchmarkMetric
 from ax.benchmark.benchmark_problem import BenchmarkProblem
-from ax.benchmark.runners.botorch_test import (
-    ParamBasedTestProblem,
-    ParamBasedTestProblemRunner,
-)
+from ax.benchmark.runners.base import BenchmarkRunner
+from ax.benchmark.runners.botorch_test import ParamBasedTestProblem
 from ax.core.objective import Objective
 from ax.core.optimization_config import OptimizationConfig
 from ax.core.parameter import ChoiceParameter, ParameterType, RangeParameter
@@ -120,7 +118,7 @@ def get_jenatton_benchmark_problem(
         name=name,
         search_space=search_space,
         optimization_config=optimization_config,
-        runner=ParamBasedTestProblemRunner(
+        runner=BenchmarkRunner(
             test_problem=Jenatton(), outcome_names=[name], noise_std=noise_std
         ),
         num_trials=num_trials,
diff --git a/ax/benchmark/runners/base.py b/ax/benchmark/runners/base.py
index 2415893be7d..3471231ebf2 100644
--- a/ax/benchmark/runners/base.py
+++ b/ax/benchmark/runners/base.py
@@ -5,7 +5,6 @@
 
 # pyre-strict
 
-from abc import ABC, abstractmethod
 from collections.abc import Iterable, Mapping
 from dataclasses import dataclass, field, InitVar
 from math import sqrt
@@ -14,6 +13,7 @@
 import numpy.typing as npt
 
 import torch
+from ax.benchmark.runners.botorch_test import ParamBasedTestProblem
 from ax.core.base_trial import BaseTrial, TrialStatus
 from ax.core.batch_trial import BatchTrial
 from ax.core.runner import Runner
@@ -28,7 +28,7 @@
 
 
 @dataclass(kw_only=True)
-class BenchmarkRunner(Runner, ABC):
+class BenchmarkRunner(Runner):
     """
     A Runner that produces both observed and ground-truth values.
 
@@ -45,9 +45,19 @@ class BenchmarkRunner(Runner, ABC):
         - If they are not deterministc, they are not supported. It is not
           conceptually clear how to benchmark such problems, so we decided to
           not over-engineer for that before such a use case arrives.
+
+    Args:
+        outcome_names: The names of the outcomes returned by the problem.
+        test_problem: A ``ParamBasedTestProblem`` from which to generate
+            deterministic data before adding noise.
+        noise_std: The standard deviation of the noise added to the data. Can be
+            a list or dict to be per-metric.
+        search_space_digest: Used to extract target fidelity and task.
     """
 
     outcome_names: list[str]
+    test_problem: ParamBasedTestProblem
+    noise_std: float | list[float] | dict[str, float] = 0.0
     # pyre-fixme[16]: Pyre doesn't understand InitVars
     search_space_digest: InitVar[SearchSpaceDigest | None] = None
     target_fidelity_and_task: Mapping[str, float | int] = field(init=False)
@@ -62,12 +72,12 @@ def __post_init__(self, search_space_digest: SearchSpaceDigest | None) -> None:
             self.target_fidelity_and_task = {}
 
     def get_Y_true(self, params: Mapping[str, TParamValue]) -> Tensor:
-        """
-        Return the ground truth values for a given arm.
+        """Evaluates the test problem.
 
-        Synthetic noise is added as part of the Runner's `run()` method.
+        Returns:
+            An `m`-dim tensor of ground truth (noiseless) evaluations.
         """
-        ...
+        return torch.atleast_1d(self.test_problem.evaluate_true(params=params))
 
     def evaluate_oracle(self, parameters: Mapping[str, TParamValue]) -> npt.NDArray:
         """
@@ -83,13 +93,19 @@ def evaluate_oracle(self, parameters: Mapping[str, TParamValue]) -> npt.NDArray:
         params = {**parameters, **self.target_fidelity_and_task}
         return self.get_Y_true(params=params).numpy()
 
-    @abstractmethod
     def get_noise_stds(self) -> dict[str, float]:
-        """
-        Return the standard errors for the synthetic noise to be applied to the
-        observed values.
-        """
-        ...
+        noise_std = self.noise_std
+        if isinstance(noise_std, float):
+            return {name: noise_std for name in self.outcome_names}
+        elif isinstance(noise_std, dict):
+            if not set(noise_std.keys()) == set(self.outcome_names):
+                raise ValueError(
+                    "Noise std must have keys equal to outcome names if given as "
+                    "a dict."
+                )
+            return noise_std
+        # list of floats
+        return dict(zip(self.outcome_names, noise_std, strict=True))
 
     def run(self, trial: BaseTrial) -> dict[str, Any]:
         """Run the trial by evaluating its parameterization(s).
diff --git a/ax/benchmark/runners/botorch_test.py b/ax/benchmark/runners/botorch_test.py
index de18d01b6eb..321675afab3 100644
--- a/ax/benchmark/runners/botorch_test.py
+++ b/ax/benchmark/runners/botorch_test.py
@@ -11,7 +11,6 @@
 from itertools import islice
 
 import torch
-from ax.benchmark.runners.base import BenchmarkRunner
 from ax.core.types import TParamValue
 from botorch.test_functions.synthetic import BaseTestProblem, ConstrainedBaseTestProblem
 from botorch.utils.transforms import normalize, unnormalize
@@ -91,48 +90,3 @@ def evaluate_true(self, params: Mapping[str, float | int]) -> torch.Tensor:
             constraints = self.botorch_problem.evaluate_slack_true(x).view(-1)
             return torch.cat([objectives, constraints], dim=-1)
         return objectives
-
-
-@dataclass(kw_only=True)
-class ParamBasedTestProblemRunner(BenchmarkRunner):
-    """
-    A Runner for evaluating `ParamBasedTestProblem`s.
-
-    Given a trial, the Runner will use its `test_problem` to evaluate the
-    problem noiselessly for each arm in the trial, and then add noise as
-    specified by the `noise_std`. It will return
-    metadata including the outcome names and values of metrics.
-
-    Args:
-        outcome_names: The names of the outcomes returned by the problem.
-        search_space_digest: Used to extract target fidelity and task.
-        test_problem: A ``ParamBasedTestProblem`` from which to generate
-            deterministic data before adding noise.
-        noise_std: The standard deviation of the noise added to the data. Can be
-            a list to be per-metric.
-    """
-
-    test_problem: ParamBasedTestProblem
-    noise_std: float | list[float] | dict[str, float] = 0.0
-
-    def get_noise_stds(self) -> dict[str, float]:
-        noise_std = self.noise_std
-        if isinstance(noise_std, float):
-            return {name: noise_std for name in self.outcome_names}
-        elif isinstance(noise_std, dict):
-            if not set(noise_std.keys()) == set(self.outcome_names):
-                raise ValueError(
-                    "Noise std must have keys equal to outcome names if given as "
-                    "a dict."
-                )
-            return noise_std
-        # list of floats
-        return dict(zip(self.outcome_names, noise_std, strict=True))
-
-    def get_Y_true(self, params: Mapping[str, TParamValue]) -> Tensor:
-        """Evaluates the test problem.
-
-        Returns:
-            An `m`-dim tensor of ground truth (noiseless) evaluations.
-        """
-        return torch.atleast_1d(self.test_problem.evaluate_true(params=params))
diff --git a/ax/benchmark/tests/problems/synthetic/hss/test_jenatton.py b/ax/benchmark/tests/problems/synthetic/hss/test_jenatton.py
index 953ea7be3aa..23a2f2737c5 100644
--- a/ax/benchmark/tests/problems/synthetic/hss/test_jenatton.py
+++ b/ax/benchmark/tests/problems/synthetic/hss/test_jenatton.py
@@ -14,7 +14,6 @@
     get_jenatton_benchmark_problem,
     jenatton_test_function,
 )
-from ax.benchmark.runners.botorch_test import ParamBasedTestProblemRunner
 from ax.core.arm import Arm
 from ax.core.data import Data
 from ax.core.experiment import Experiment
@@ -106,10 +105,7 @@ def test_create_problem(self) -> None:
         self.assertEqual(metric.name, "Jenatton")
         self.assertTrue(objective.minimize)
         self.assertTrue(metric.lower_is_better)
-        self.assertEqual(
-            assert_is_instance(problem.runner, ParamBasedTestProblemRunner).noise_std,
-            0.0,
-        )
+        self.assertEqual(problem.runner.noise_std, 0.0)
         self.assertFalse(assert_is_instance(metric, BenchmarkMetric).observe_noise_sd)
 
         problem = get_jenatton_benchmark_problem(
@@ -118,10 +114,7 @@ def test_create_problem(self) -> None:
         objective = problem.optimization_config.objective
         metric = objective.metric
         self.assertTrue(metric.lower_is_better)
-        self.assertEqual(
-            assert_is_instance(problem.runner, ParamBasedTestProblemRunner).noise_std,
-            0.1,
-        )
+        self.assertEqual(problem.runner.noise_std, 0.1)
         self.assertTrue(assert_is_instance(metric, BenchmarkMetric).observe_noise_sd)
 
     def test_fetch_trial_data(self) -> None:
diff --git a/ax/benchmark/tests/problems/test_mixed_integer_problems.py b/ax/benchmark/tests/problems/test_mixed_integer_problems.py
index 694dfd63a66..c744c50f516 100644
--- a/ax/benchmark/tests/problems/test_mixed_integer_problems.py
+++ b/ax/benchmark/tests/problems/test_mixed_integer_problems.py
@@ -15,10 +15,7 @@
     get_discrete_hartmann,
     get_discrete_rosenbrock,
 )
-from ax.benchmark.runners.botorch_test import (
-    BoTorchTestProblem,
-    ParamBasedTestProblemRunner,
-)
+from ax.benchmark.runners.botorch_test import BoTorchTestProblem
 from ax.core.arm import Arm
 from ax.core.parameter import ParameterType
 from ax.core.trial import Trial
@@ -37,7 +34,7 @@ def test_problems(self) -> None:
             name = problem_cls.__name__
             problem = constructor()
             self.assertEqual(f"Discrete {name}", problem.name)
-            runner = assert_is_instance(problem.runner, ParamBasedTestProblemRunner)
+            runner = problem.runner
             test_problem = assert_is_instance(runner.test_problem, BoTorchTestProblem)
             botorch_problem = test_problem.botorch_problem
             self.assertIsInstance(botorch_problem, problem_cls)
@@ -99,7 +96,7 @@ def test_problems(self) -> None:
         ]
 
         for problem, params, expected_arg in cases:
-            runner = assert_is_instance(problem.runner, ParamBasedTestProblemRunner)
+            runner = problem.runner
             test_problem = assert_is_instance(runner.test_problem, BoTorchTestProblem)
             trial = Trial(experiment=MagicMock())
             # pyre-fixme: Incompatible parameter type [6]: In call
diff --git a/ax/benchmark/tests/runners/test_botorch_test_problem.py b/ax/benchmark/tests/runners/test_botorch_test_problem.py
index 9dcba5c4872..67ed96f4095 100644
--- a/ax/benchmark/tests/runners/test_botorch_test_problem.py
+++ b/ax/benchmark/tests/runners/test_botorch_test_problem.py
@@ -16,10 +16,8 @@
 
 import torch
 from ax.benchmark.problems.synthetic.hss.jenatton import get_jenatton_benchmark_problem
-from ax.benchmark.runners.botorch_test import (
-    BoTorchTestProblem,
-    ParamBasedTestProblemRunner,
-)
+from ax.benchmark.runners.base import BenchmarkRunner
+from ax.benchmark.runners.botorch_test import BoTorchTestProblem
 from ax.benchmark.runners.surrogate import SurrogateTestFunction
 from ax.core.arm import Arm
 from ax.core.base_trial import TrialStatus
@@ -154,7 +152,7 @@ def test_synthetic_runner(self) -> None:
                 outcome_names = ["branin"]
 
             # Set up runner
-            runner = ParamBasedTestProblemRunner(
+            runner = BenchmarkRunner(
                 test_problem=test_problem,
                 outcome_names=outcome_names,
                 noise_std=noise_std,
@@ -291,15 +289,15 @@ def test_synthetic_runner(self) -> None:
                 with self.assertRaisesRegex(
                     UnsupportedError, "serialize_init_args is not a supported method"
                 ):
-                    ParamBasedTestProblemRunner.serialize_init_args(obj=runner)
+                    BenchmarkRunner.serialize_init_args(obj=runner)
                 with self.assertRaisesRegex(
                     UnsupportedError, "deserialize_init_args is not a supported method"
                 ):
-                    ParamBasedTestProblemRunner.deserialize_init_args({})
+                    BenchmarkRunner.deserialize_init_args({})
 
     def test_botorch_test_problem_runner_heterogeneous_noise(self) -> None:
         for noise_std in [[0.1, 0.05], {"objective": 0.1, "constraint": 0.05}]:
-            runner = ParamBasedTestProblemRunner(
+            runner = BenchmarkRunner(
                 test_problem=BoTorchTestProblem(
                     botorch_problem=ConstrainedHartmann(dim=6)
                 ),
diff --git a/ax/benchmark/tests/test_benchmark_problem.py b/ax/benchmark/tests/test_benchmark_problem.py
index 886d9f85cb8..b8f948a1607 100644
--- a/ax/benchmark/tests/test_benchmark_problem.py
+++ b/ax/benchmark/tests/test_benchmark_problem.py
@@ -14,10 +14,8 @@
 from ax.benchmark.benchmark_metric import BenchmarkMetric
 
 from ax.benchmark.benchmark_problem import BenchmarkProblem, create_problem_from_botorch
-from ax.benchmark.runners.botorch_test import (
-    BoTorchTestProblem,
-    ParamBasedTestProblemRunner,
-)
+from ax.benchmark.runners.base import BenchmarkRunner
+from ax.benchmark.runners.botorch_test import BoTorchTestProblem
 from ax.core.objective import MultiObjective, Objective
 from ax.core.optimization_config import (
     MultiObjectiveOptimizationConfig,
@@ -54,7 +52,7 @@ def test_inference_value_not_implemented(self) -> None:
             for name in ["Branin", "Currin"]
         ]
         optimization_config = OptimizationConfig(objective=objectives[0])
-        runner = ParamBasedTestProblemRunner(
+        runner = BenchmarkRunner(
             test_problem=BoTorchTestProblem(botorch_problem=Branin()),
             outcome_names=["foo"],
         )
@@ -215,7 +213,7 @@ def _test_constrained_from_botorch(
             observe_noise_sd=observe_noise_sd,
             noise_std=noise_std,
         )
-        runner = assert_is_instance(ax_problem.runner, ParamBasedTestProblemRunner)
+        runner = ax_problem.runner
         test_problem = assert_is_instance(runner.test_problem, BoTorchTestProblem)
         botorch_problem = assert_is_instance(
             test_problem.botorch_problem, ConstrainedBaseTestProblem
diff --git a/ax/storage/tests/test_registry_bundle.py b/ax/storage/tests/test_registry_bundle.py
index 4add5eb266b..1c775db8dac 100644
--- a/ax/storage/tests/test_registry_bundle.py
+++ b/ax/storage/tests/test_registry_bundle.py
@@ -6,7 +6,6 @@
 # pyre-strict
 
 from ax.benchmark.benchmark_metric import BenchmarkMetric
-from ax.benchmark.runners.botorch_test import ParamBasedTestProblemRunner
 from ax.metrics.branin import BraninMetric
 from ax.runners.synthetic import SyntheticRunner
 from ax.storage.registry_bundle import RegistryBundle
@@ -26,7 +25,7 @@ def test_from_registry_bundles(self) -> None:
 
         right = RegistryBundle(
             metric_clss={BenchmarkMetric: None},
-            runner_clss={ParamBasedTestProblemRunner: None},
+            runner_clss={SyntheticRunner: None},
             json_encoder_registry={},
             json_class_encoder_registry={},
             json_decoder_registry={},
@@ -41,4 +40,3 @@ def test_from_registry_bundles(self) -> None:
         self.assertIn(BraninMetric, combined.encoder_registry)
         self.assertIn(SyntheticRunner, combined.encoder_registry)
         self.assertIn(BenchmarkMetric, combined.encoder_registry)
-        self.assertIn(ParamBasedTestProblemRunner, combined.encoder_registry)
diff --git a/ax/utils/testing/benchmark_stubs.py b/ax/utils/testing/benchmark_stubs.py
index f5a7a72b717..0c462ac32eb 100644
--- a/ax/utils/testing/benchmark_stubs.py
+++ b/ax/utils/testing/benchmark_stubs.py
@@ -15,10 +15,8 @@
 from ax.benchmark.benchmark_metric import BenchmarkMetric
 from ax.benchmark.benchmark_problem import BenchmarkProblem, create_problem_from_botorch
 from ax.benchmark.benchmark_result import AggregatedBenchmarkResult, BenchmarkResult
-from ax.benchmark.runners.botorch_test import (
-    ParamBasedTestProblem,
-    ParamBasedTestProblemRunner,
-)
+from ax.benchmark.runners.base import BenchmarkRunner
+from ax.benchmark.runners.botorch_test import ParamBasedTestProblem
 from ax.benchmark.runners.surrogate import SurrogateTestFunction
 from ax.core.experiment import Experiment
 from ax.core.objective import MultiObjective, Objective
@@ -105,9 +103,7 @@ def get_soo_surrogate_test_function(lazy: bool = True) -> SurrogateTestFunction:
 def get_soo_surrogate() -> BenchmarkProblem:
     experiment = get_branin_experiment(with_completed_trial=True)
     test_function = get_soo_surrogate_test_function()
-    runner = ParamBasedTestProblemRunner(
-        test_problem=test_function, outcome_names=["branin"]
-    )
+    runner = BenchmarkRunner(test_problem=test_function, outcome_names=["branin"])
 
     observe_noise_sd = True
     objective = Objective(
@@ -144,9 +140,7 @@ def get_moo_surrogate() -> BenchmarkProblem:
         outcome_names=outcome_names,
         get_surrogate_and_datasets=lambda: (surrogate, []),
     )
-    runner = ParamBasedTestProblemRunner(
-        test_problem=test_function, outcome_names=outcome_names
-    )
+    runner = BenchmarkRunner(test_problem=test_function, outcome_names=outcome_names)
     observe_noise_sd = True
     optimization_config = MultiObjectiveOptimizationConfig(
         objective=MultiObjective(