diff --git a/tests/outputs/results (CoT).CSV b/tests/outputs/results (CoT).CSV
new file mode 100644
index 0000000..95b2c48
--- /dev/null
+++ b/tests/outputs/results (CoT).CSV	
@@ -0,0 +1,13 @@
+,model name,dataname,expected,human,AI,unsure,invalid
+0,Microsoft Phi,LDAG,human,13,14,12,20
+1,Microsoft Phi,HLTC,human,12,11,19,17
+2,Microsoft Phi,LDAG,AI,10,18,14,17
+3,Microsoft Phi,HLTC,AI,14,13,23,9
+4,Gemma 2,LDAG,human,35,24,0,0
+5,Gemma 2,HLTC,human,45,14,0,0
+6,Gemma 2,LDAG,AI,51,8,0,0
+7,Gemma 2,HLTC,AI,42,17,0,0
+8,Tinyllama,LDAG,human,11,4,34,10
+9,Tinyllama,HLTC,human,13,5,30,11
+10,Tinyllama,LDAG,AI,11,5,31,12
+11,Tinyllama,HLTC,AI,11,3,35,10
diff --git a/tests/outputs/results (Multi-Shot).CSV b/tests/outputs/results (Multi-Shot).CSV
new file mode 100644
index 0000000..74264db
--- /dev/null
+++ b/tests/outputs/results (Multi-Shot).CSV	
@@ -0,0 +1,13 @@
+,model name,dataname,expected,human,AI,unsure,invalid
+0,Microsoft Phi,LDAG,human,1,10,46,2
+1,Microsoft Phi,HLTC,human,7,6,44,2
+2,Microsoft Phi,LDAG,AI,7,4,43,5
+3,Microsoft Phi,HLTC,AI,4,7,47,1
+4,Gemma 2,LDAG,human,24,35,0,0
+5,Gemma 2,HLTC,human,48,11,0,0
+6,Gemma 2,LDAG,AI,49,10,0,0
+7,Gemma 2,HLTC,AI,48,11,0,0
+8,Tinyllama,LDAG,human,24,5,28,2
+9,Tinyllama,HLTC,human,17,3,36,3
+10,Tinyllama,LDAG,AI,14,3,37,5
+11,Tinyllama,HLTC,AI,17,1,39,2
diff --git a/tests/outputs/results (classic).CSV b/tests/outputs/results (classic).CSV
new file mode 100644
index 0000000..afb562c
--- /dev/null
+++ b/tests/outputs/results (classic).CSV	
@@ -0,0 +1,13 @@
+,model name,dataname,expected,human,AI,unsure,invalid
+0,Microsoft Phi,LDAG,human,3,4,48,4
+1,Microsoft Phi,HLTC,human,7,6,42,4
+2,Microsoft Phi,LDAG,AI,5,9,43,2
+3,Microsoft Phi,HLTC,AI,4,4,49,2
+4,Gemma 2,LDAG,human,38,21,0,0
+5,Gemma 2,HLTC,human,47,12,0,0
+6,Gemma 2,LDAG,AI,51,8,0,0
+7,Gemma 2,HLTC,AI,46,13,0,0
+8,Tinyllama,LDAG,human,13,3,37,6
+9,Tinyllama,HLTC,human,9,3,40,7
+10,Tinyllama,LDAG,AI,8,5,40,6
+11,Tinyllama,HLTC,AI,11,4,37,7