diff --git a/scripts/welch_ttest.py b/scripts/welch_ttest.py
index ace25a2..d8a8097 100755
--- a/scripts/welch_ttest.py
+++ b/scripts/welch_ttest.py
@@ -2,15 +2,20 @@
 
 import argparse
 import json
+import sys
 from scipy import stats
 
 parser = argparse.ArgumentParser()
-parser.add_argument("file", help="JSON file with benchmark results")
+parser.add_argument("file", help="JSON file with two benchmark results")
 args = parser.parse_args()
 
 with open(args.file) as f:
     results = json.load(f)["results"]
 
+if len(results) != 2:
+    print("The input file has to contain exactly two benchmarks")
+    sys.exit(1)
+
 a, b = [x["command"] for x in results[:2]]
 X, Y = [x["times"] for x in results[:2]]
 
@@ -25,4 +30,4 @@ print("p < {} = {}\n".format(th, dispose))
 if dispose:
     print("There is a difference between the two benchmarks.")
 else:
-    print("The two benchmarks are almost the same.")
\ No newline at end of file
+    print("The two benchmarks are almost the same.")