diff --git a/CHANGELOG.md b/CHANGELOG.md
index 80c95fb0..b46b52ba 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -20,6 +20,7 @@
   and rerun `create-index`.
 ### Added
 
+- `evaluations run --retrieval-limit N`: candidates each database fetches during the retrieval benchmark, overriding the dataset's `retrieval_limit`.
 - `mtrag_federated` evaluation dataset and its reference config `evaluations/configs/mtrag_federated.yaml`: MTRAG ClapNQ partitioned by article title into `n` collections, scored on retrieval only with Recall@5/@10, nDCG@5 and MAP. `python -m evaluations.datasets.mtrag_federated --config REF --n N --out PATH` builds the partition and emits the config that searches it.
 
 ### Fixed
diff --git a/evaluations/evaluations/benchmark.py b/evaluations/evaluations/benchmark.py
index 182d5977..d4541045 100644
--- a/evaluations/evaluations/benchmark.py
+++ b/evaluations/evaluations/benchmark.py
@@ -41,6 +41,7 @@ async def evaluate_dataset(
     vacuum_interval: int = 100,
     multimodal_only: bool = False,
     judge_model: ModelConfig | None = None,
+    retrieval_limit: int | None = None,
     target: Target = "rag-capability",
     capability_model: ModelConfig | None = None,
     case_ids: set[str] | None = None,
@@ -72,6 +73,7 @@ async def evaluate_dataset(
             db_path=db_path,
             multimodal_only=multimodal_only,
             document_filter=document_filter,
+            retrieval_limit=retrieval_limit,
         )
 
     if not skip_qa:
@@ -169,6 +171,14 @@ def run(
         None, "--limit", help="Limit number of test cases for both retrieval and QA."
     ),
     name: str | None = typer.Option(None, "--name", help="Override evaluation name."),
+    retrieval_limit: int | None = typer.Option(
+        None,
+        "--retrieval-limit",
+        help=(
+            "Candidates each database fetches, overriding the dataset's. "
+            "Sets how deep hybrid search looks before its results are scored."
+        ),
+    ),
     vacuum_interval: int = typer.Option(
         100, "--vacuum-interval", help="Vacuum every N documents during DB population."
     ),
@@ -235,6 +245,7 @@ def run(
             vacuum_interval=vacuum_interval,
             multimodal_only=multimodal_only,
             judge_model=judge_model_config,
+            retrieval_limit=retrieval_limit,
             target=target_value,
             capability_model=capability_model_config,
             case_ids=_load_case_ids(filter_ids),
diff --git a/evaluations/evaluations/retrieval.py b/evaluations/evaluations/retrieval.py
index 9768c587..7a3e36c4 100644
--- a/evaluations/evaluations/retrieval.py
+++ b/evaluations/evaluations/retrieval.py
@@ -24,6 +24,7 @@ async def run_retrieval_benchmark(
     db_path: Path | None = None,
     multimodal_only: bool = False,
     document_filter: str | None = None,
+    retrieval_limit: int | None = None,
 ) -> dict[str, float] | None:
     if spec.retrieval_loader is None or spec.retrieval_mapper is None:
         console.print("Skipping retrieval benchmark; no retrieval config.")
@@ -72,6 +73,7 @@ async def run_retrieval_benchmark(
         evaluators=list(spec.retrieval_evaluators),
     )
 
+    fetch = retrieval_limit or spec.retrieval_limit
     db = (
         None
         if spec.uses_configured_databases(config, db_path)
@@ -82,7 +84,7 @@ async def run_retrieval_benchmark(
         async def retrieval_target(question: str) -> list[str]:
             chunks = await rag.search(
                 query=question,
-                limit=spec.retrieval_limit,
+                limit=fetch,
                 include_images=False,
                 filter=document_filter,
             )
diff --git a/evaluations/tests/test_mtrag_federated.py b/evaluations/tests/test_mtrag_federated.py
index fd93357d..2368ada5 100644
--- a/evaluations/tests/test_mtrag_federated.py
+++ b/evaluations/tests/test_mtrag_federated.py
@@ -17,6 +17,22 @@ from evaluations.datasets.mtrag_federated import (
 )
 
 
+def _smoke_config():
+    """A config placing two databases, so the run resolves a federated client."""
+    from haiku.rag.config.models import AppConfig
+
+    return AppConfig.model_validate(
+        {
+            "lancedb": {
+                "databases": {
+                    "clapnq_0": "/tmp/a.lancedb",
+                    "clapnq_1": "/tmp/b.lancedb",
+                }
+            }
+        }
+    )
+
+
 def record(passage_id: str, title: str) -> dict[str, str]:
     return {"_id": passage_id, "title": title, "text": f"text of {passage_id}"}
 
@@ -193,3 +209,42 @@ class TestPoolComposition:
 
     def test_the_default_budget_clears_the_gold_floor(self) -> None:
         assert DEFAULT_BUDGET > GOLD_TITLE_FLOOR
+
+
+class TestRetrievalLimitOverride:
+    async def test_override_replaces_the_spec_value(self, monkeypatch) -> None:
+        """Fetch depth is a run knob: hybrid search degenerates below roughly 50
+        candidates, so every regime would otherwise need its own dataset."""
+        seen: list[int | None] = []
+
+        async def fake_search(self, query, limit=None, **kwargs):  # noqa: ANN001
+            seen.append(limit)
+            return []
+
+        from haiku.rag.client import HaikuRAG
+
+        monkeypatch.setattr(HaikuRAG, "search", fake_search)
+        from evaluations.retrieval import run_retrieval_benchmark
+
+        await run_retrieval_benchmark(
+            MTRAG_FEDERATED_SPEC,
+            _smoke_config(),
+            limit=1,
+            retrieval_limit=77,
+        )
+        assert seen and set(seen) == {77}
+
+    async def test_spec_value_is_the_default(self, monkeypatch) -> None:
+        seen: list[int | None] = []
+
+        async def fake_search(self, query, limit=None, **kwargs):  # noqa: ANN001
+            seen.append(limit)
+            return []
+
+        from haiku.rag.client import HaikuRAG
+
+        monkeypatch.setattr(HaikuRAG, "search", fake_search)
+        from evaluations.retrieval import run_retrieval_benchmark
+
+        await run_retrieval_benchmark(MTRAG_FEDERATED_SPEC, _smoke_config(), limit=1)
+        assert seen and set(seen) == {MTRAG_FEDERATED_SPEC.retrieval_limit}