diff --git a/libs/partners/anthropic/Makefile b/libs/partners/anthropic/Makefile
index 275e3470510..fca7a1c2efc 100644
--- a/libs/partners/anthropic/Makefile
+++ b/libs/partners/anthropic/Makefile
@@ -15,7 +15,7 @@ test tests:
 	uv run --group test pytest -vvv $(PYTEST_EXTRA) --disable-socket --allow-unix-socket $(TEST_FILE)
 
 integration_test integration_tests:
-	uv run --group test --group test_integration pytest -v --tb=short -p no:benchmark -n auto --timeout 30 $(TEST_FILE)
+	uv run --group test --group test_integration pytest -v --tb=short -n auto --timeout 30 $(TEST_FILE)
 
 test_watch:
 	uv run --group test ptw --snapshot-update --now . -- -vv $(TEST_FILE)
diff --git a/libs/partners/chroma/Makefile b/libs/partners/chroma/Makefile
index 0617411c2ab..5248da9278d 100644
--- a/libs/partners/chroma/Makefile
+++ b/libs/partners/chroma/Makefile
@@ -15,7 +15,7 @@ test tests:
 	uv run --group test pytest $(PYTEST_EXTRA) --disable-socket --allow-unix-socket $(TEST_FILE)
 
 integration_test integration_tests:
-	uv run --group test --group test_integration pytest -v --tb=short -p no:benchmark -n auto $(TEST_FILE)
+	uv run --group test --group test_integration pytest -v --tb=short -n auto $(TEST_FILE)
 
 test_watch:
 	uv run --group test ptw --snapshot-update --now . -- -vv $(TEST_FILE)
diff --git a/libs/partners/deepseek/Makefile b/libs/partners/deepseek/Makefile
index 0f85160ded5..f7ae818ca04 100644
--- a/libs/partners/deepseek/Makefile
+++ b/libs/partners/deepseek/Makefile
@@ -21,7 +21,7 @@ test_watch:
 
 # integration tests are run without the --disable-socket flag to allow network calls
 integration_test integration_tests:
-	uv run --group test --group test_integration pytest -v --tb=short -p no:benchmark -n auto --timeout=30 $(TEST_FILE)
+	uv run --group test --group test_integration pytest -v --tb=short -n auto --timeout=30 $(TEST_FILE)
 
 ######################
 # LINTING AND FORMATTING
diff --git a/libs/partners/exa/Makefile b/libs/partners/exa/Makefile
index ca5a8a619e4..e01b9356c10 100644
--- a/libs/partners/exa/Makefile
+++ b/libs/partners/exa/Makefile
@@ -16,7 +16,7 @@ test:
 	uv run --group test --group test_integration pytest $(PYTEST_EXTRA) $(TEST_FILE)
 
 integration_test integration_tests:
-	uv run --group test --group test_integration pytest -v --tb=short -p no:benchmark -n auto $(PYTEST_EXTRA) $(TEST_FILE)
+	uv run --group test --group test_integration pytest -v --tb=short -n auto $(PYTEST_EXTRA) $(TEST_FILE)
 
 tests:
 	uv run --group test pytest $(PYTEST_EXTRA) $(TEST_FILE)
diff --git a/libs/partners/fireworks/Makefile b/libs/partners/fireworks/Makefile
index 8749d427b3b..bb09a646233 100644
--- a/libs/partners/fireworks/Makefile
+++ b/libs/partners/fireworks/Makefile
@@ -15,7 +15,7 @@ test tests:
 	uv run --group test pytest $(PYTEST_EXTRA) --disable-socket --allow-unix-socket $(TEST_FILE)
 
 integration_test integration_tests:
-	uv run --group test --group test_integration pytest -v --tb=short -p no:benchmark -n auto $(TEST_FILE)
+	uv run --group test --group test_integration pytest -v --tb=short -n auto $(TEST_FILE)
 
 test_watch:
 	uv run --group test ptw --snapshot-update --now . -- -vv $(TEST_FILE)
diff --git a/libs/partners/groq/Makefile b/libs/partners/groq/Makefile
index 345f2381bde..8f29852825a 100644
--- a/libs/partners/groq/Makefile
+++ b/libs/partners/groq/Makefile
@@ -16,7 +16,7 @@ test tests:
 	uv run --group test pytest $(PYTEST_EXTRA) --disable-socket --allow-unix-socket $(TEST_FILE)
 
 integration_test integration_tests:
-	uv run --group test --group test_integration pytest -v --tb=short -p no:benchmark -n auto --retries 3 --retry-delay 1 $(TEST_FILE)
+	uv run --group test --group test_integration pytest -v --tb=short -n auto --retries 3 --retry-delay 1 $(TEST_FILE)
 
 test_watch:
 	uv run --group test ptw --snapshot-update --now . -- -vv $(TEST_FILE)
diff --git a/libs/partners/huggingface/Makefile b/libs/partners/huggingface/Makefile
index 7e32e2e0bf0..e2bd889e366 100644
--- a/libs/partners/huggingface/Makefile
+++ b/libs/partners/huggingface/Makefile
@@ -16,7 +16,7 @@ test tests:
 	uv run --group test pytest $(PYTEST_EXTRA) --disable-socket --allow-unix-socket $(TEST_FILE)
 
 integration_test integration_tests:
-	uv run --group test --group test_integration pytest -v --tb=short -p no:benchmark -n auto $(TEST_FILE)
+	uv run --group test --group test_integration pytest -v --tb=short -n auto $(TEST_FILE)
 
 test_watch:
 	uv run --group test ptw --snapshot-update --now . -- -vv $(TEST_FILE)
diff --git a/libs/partners/mistralai/Makefile b/libs/partners/mistralai/Makefile
index b7fa018b6eb..e2365801c12 100644
--- a/libs/partners/mistralai/Makefile
+++ b/libs/partners/mistralai/Makefile
@@ -21,7 +21,7 @@ test_watch:
 
 
 integration_test integration_tests:
-	uv run --group test --group test_integration pytest -v --tb=short -p no:benchmark -n auto $(TEST_FILE)
+	uv run --group test --group test_integration pytest -v --tb=short -n auto $(TEST_FILE)
 
 
 ######################
diff --git a/libs/partners/nomic/Makefile b/libs/partners/nomic/Makefile
index 8b99758fe30..895e42a9a50 100644
--- a/libs/partners/nomic/Makefile
+++ b/libs/partners/nomic/Makefile
@@ -16,7 +16,7 @@ test:
 	uv run --group test --group test_integration pytest $(PYTEST_EXTRA) $(TEST_FILE)
 
 integration_test integration_tests:
-	uv run --group test --group test_integration pytest -v --tb=short -p no:benchmark -n auto $(PYTEST_EXTRA) $(TEST_FILE)
+	uv run --group test --group test_integration pytest -v --tb=short -n auto $(PYTEST_EXTRA) $(TEST_FILE)
 
 tests:
 	uv run --group test pytest $(PYTEST_EXTRA) $(TEST_FILE)
diff --git a/libs/partners/ollama/Makefile b/libs/partners/ollama/Makefile
index f3e8952e115..7698174d60c 100644
--- a/libs/partners/ollama/Makefile
+++ b/libs/partners/ollama/Makefile
@@ -27,7 +27,7 @@ test_watch:
 
 # integration tests are run without the --disable-socket flag to allow network calls
 integration_test:
-	OLLAMA_TEST_MODEL=$(OLLAMA_TEST_MODEL) OLLAMA_REASONING_TEST_MODEL=$(OLLAMA_REASONING_TEST_MODEL) uv run --group test --group test_integration pytest -v --tb=short -p no:benchmark -n auto $(TEST_FILE)
+	OLLAMA_TEST_MODEL=$(OLLAMA_TEST_MODEL) OLLAMA_REASONING_TEST_MODEL=$(OLLAMA_REASONING_TEST_MODEL) uv run --group test --group test_integration pytest -v --tb=short -n auto $(TEST_FILE)
 
 # CI integration tests - disabled until ollama service is configured in CI
 
diff --git a/libs/partners/openai/Makefile b/libs/partners/openai/Makefile
index 7ba6631f0c5..087b2c9c04f 100644
--- a/libs/partners/openai/Makefile
+++ b/libs/partners/openai/Makefile
@@ -25,7 +25,7 @@ test tests:
 	TIKTOKEN_CACHE_DIR=tiktoken_cache uv run --group test pytest $(PYTEST_EXTRA) --disable-socket --allow-unix-socket $(TEST_FILE)
 
 integration_test integration_tests:
-	uv run --group test --group test_integration pytest -v --tb=short -p no:benchmark -n auto $(TEST_FILE)
+	uv run --group test --group test_integration pytest -v --tb=short -n auto $(TEST_FILE)
 
 # Run VCR cassette-backed integration tests in playback-only mode (no API keys needed).
 # Catches stale cassettes caused by test input changes without re-recording.
diff --git a/libs/partners/openrouter/Makefile b/libs/partners/openrouter/Makefile
index b6c362021e5..4f0f537496e 100644
--- a/libs/partners/openrouter/Makefile
+++ b/libs/partners/openrouter/Makefile
@@ -21,7 +21,7 @@ test_watch:
 
 # integration tests are run without the --disable-socket flag to allow network calls
 integration_test integration_tests:
-	uv run --group test --group test_integration pytest -v --tb=short -p no:benchmark -n auto --timeout=120 $(TEST_FILE)
+	uv run --group test --group test_integration pytest -v --tb=short -n auto --timeout=120 $(TEST_FILE)
 
 ######################
 # LINTING AND FORMATTING
diff --git a/libs/partners/perplexity/Makefile b/libs/partners/perplexity/Makefile
index 0e06499ba84..ca7b025aacc 100644
--- a/libs/partners/perplexity/Makefile
+++ b/libs/partners/perplexity/Makefile
@@ -19,7 +19,7 @@ test_watch:
 	uv run --group test ptw --snapshot-update --now . -- -vv $(TEST_FILE)
 
 integration_test integration_tests:
-	uv run --group test --group test_integration pytest -v --tb=short -p no:benchmark -n auto $(TEST_FILE)
+	uv run --group test --group test_integration pytest -v --tb=short -n auto $(TEST_FILE)
 
 ######################
 # LINTING AND FORMATTING
diff --git a/libs/partners/qdrant/Makefile b/libs/partners/qdrant/Makefile
index 8c79429edac..c53ee48ac9e 100644
--- a/libs/partners/qdrant/Makefile
+++ b/libs/partners/qdrant/Makefile
@@ -16,7 +16,7 @@ test tests:
 	uv run --group test pytest $(PYTEST_EXTRA) --disable-socket --allow-unix-socket $(TEST_FILE)
 
 integration_test integration_tests:
-	uv run --group test --group test_integration pytest -v --tb=short -p no:benchmark -n auto $(TEST_FILE)
+	uv run --group test --group test_integration pytest -v --tb=short -n auto $(TEST_FILE)
 
 test_watch:
 	uv run --group test ptw --snapshot-update --now . -- -vv $(TEST_FILE)
diff --git a/libs/partners/xai/Makefile b/libs/partners/xai/Makefile
index bd41b6a2e83..d92cf3637ab 100644
--- a/libs/partners/xai/Makefile
+++ b/libs/partners/xai/Makefile
@@ -19,7 +19,7 @@ test_watch:
 	uv run --group test ptw --snapshot-update --now . -- -vv $(TEST_FILE)
 
 integration_test integration_tests:
-	uv run --group test --group test_integration pytest -v --tb=short -p no:benchmark -n auto $(TEST_FILE)
+	uv run --group test --group test_integration pytest -v --tb=short -n auto $(TEST_FILE)
 
 ######################
 # LINTING AND FORMATTING