diff --git a/Makefile b/Makefile
index 04b96d8..13ac948 100644
--- a/Makefile
+++ b/Makefile
@@ -29,11 +29,11 @@ monitor-log: ## Start background metric logger
 benchmark-setup: ## Ensure toolboxes and test models are ready
 	@bash scripts/benchmark/setup.sh
 
-benchmark-baseline: ## Capture pre-optimization baseline
-	@bash bin/benchmark baseline
+benchmark-baseline: ## Capture pre-optimization baseline (supports ARGS="--max-size 20 --skip-longctx")
+	@bash bin/benchmark baseline $(ARGS)
 
-benchmark: ## Run full benchmark suite
-	@bash bin/benchmark run
+benchmark: ## Run full benchmark suite (supports ARGS="--tag NAME --max-size 20")
+	@bash bin/benchmark run $(ARGS)
 
 benchmark-compare: ## Compare two benchmark runs (usage: make benchmark-compare BEFORE=dir AFTER=dir)
 	@bash bin/benchmark compare $(BEFORE) $(AFTER)