diff --git a/pyproject.toml b/pyproject.toml
index da26b04..b11c7bd 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -37,6 +37,12 @@ homepage = "https://instructlab.ai"
 source = "https://github.com/instructlab/eval"
 issues = "https://github.com/instructlab/eval/issues"
 
+[project.entry-points."instructlab.eval.evaluator"]
+"mmlu" = "instructlab.eval.mmlu:MMLUEvaluator"
+"mmlu_branch" = "instructlab.eval.mmlu:MMLUBranchEvaluator"
+"mt_bench" = "instructlab.eval.mt_bench:MTBenchEvaluator"
+"mt_bench_branch" = "instructlab.eval.mt_bench:MTBenchBranchEvaluator"
+
 [tool.setuptools_scm]
 version_file = "src/instructlab/eval/_version.py"
 # do not include +gREV local version, required for Test PyPI upload
diff --git a/src/instructlab/eval/evaluator.py b/src/instructlab/eval/evaluator.py
index f62b254..7972aec 100644
--- a/src/instructlab/eval/evaluator.py
+++ b/src/instructlab/eval/evaluator.py
@@ -6,5 +6,7 @@ class Evaluator:
     Parent class for Evaluators
     """
 
+    name: str
+
     def __init__(self) -> None:
         pass
diff --git a/src/instructlab/eval/mmlu.py b/src/instructlab/eval/mmlu.py
index 962b794..a3d9f6c 100644
--- a/src/instructlab/eval/mmlu.py
+++ b/src/instructlab/eval/mmlu.py
@@ -84,6 +84,8 @@ class MMLUEvaluator(Evaluator):
         batch_size   number of GPUs
     """
 
+    name = "mmlu"
+
     def __init__(
         self,
         model_path,
@@ -147,6 +149,8 @@ class MMLUBranchEvaluator(Evaluator):
         batch_size  number of GPUs
     """
 
+    name = "mmlu_branch"
+
     def __init__(
         self,
         model_path,
diff --git a/src/instructlab/eval/mt_bench.py b/src/instructlab/eval/mt_bench.py
index 3a5f12f..3043d10 100644
--- a/src/instructlab/eval/mt_bench.py
+++ b/src/instructlab/eval/mt_bench.py
@@ -22,6 +22,8 @@ class MTBenchEvaluator(Evaluator):
         max_workers         Max parallel workers to run the evaluation with
     """
 
+    name = "mt_bench"
+
     def __init__(
         self,
         model_name: str,
@@ -82,6 +84,8 @@ class MTBenchBranchEvaluator(Evaluator):
         max_workers             Max parallel workers to run the evaluation with
     """
 
+    name = "mt_bench_branch"
+
     def __init__(
         self,
         model_name: str,
diff --git a/tests/test_project.py b/tests/test_project.py
new file mode 100644
index 0000000..13c4dbc
--- /dev/null
+++ b/tests/test_project.py
@@ -0,0 +1,29 @@
+# SPDX-License-Identifier: Apache-2.0
+# Standard
+from importlib.metadata import entry_points
+
+# First Party
+from instructlab.eval.evaluator import Evaluator
+from instructlab.eval.mmlu import MMLUBranchEvaluator, MMLUEvaluator
+from instructlab.eval.mt_bench import MTBenchBranchEvaluator, MTBenchEvaluator
+
+
+def test_evaluator_eps():
+    expected = {
+        "mmlu": MMLUEvaluator,
+        "mmlu_branch": MMLUBranchEvaluator,
+        "mt_bench": MTBenchEvaluator,
+        "mt_bench_branch": MTBenchBranchEvaluator,
+    }
+    eps = entry_points(group="instructlab.eval.evaluator")
+    found = {}
+    for ep in eps:
+        # different project
+        if not ep.module.startswith("instructlab.eval"):
+            continue
+        evaluator = ep.load()
+        assert issubclass(evaluator, Evaluator)
+        assert evaluator.name == ep.name
+        found[ep.name] = evaluator
+
+    assert found == expected