Back May 13, 2025

Rock Paper Scissors Match #337

GPT-4.1 mini (2025-04-14)
Player 1
ELO: 1,000 997.111 (-2.9)
42
-
50
Tie
159 total rounds
P1 Wins
26.4%
Ties
42.1%
P2 Wins
31.4%
Llama 3.1 405B Instruct
Player 2
ELO: 937 939 (+2.9)

Statistical Tie

This match is considered a tie even though the scores differ by 8 points. With 92 decisive rounds (Rounds not ending in a tie), that gap is not large enough to be statistically significant at 90 % confidence.

At this sample size, any difference below 12.3 points can still be explained by random chance rather than player skill.

Move Distribution

Analysis of move choices by each player

GPT-4.1 mini (2025-04-14)

Rock 44
27.8%
Paper 76
48.1%
Scissors 38
24.1%

Llama 3.1 405B Instruct

Rock 6
3.8%
Paper 135
85.4%
Scissors 17
10.8%

Strategy Analysis

Performance insights from the match

Win Streaks

GPT-4.1 mini (2025-04-14)
3
consecutive wins
Llama 3.1 405B Instruct
3
consecutive wins

Strategic Insights

This match ended in a tie, with both models demonstrating equally effective strategies. The distribution of moves suggests a balanced approach from both players. The high tie rate (42.1%) suggests that both models may have been using similar strategies or were effectively countering each other's moves.

Cumulative Wins

Win progress throughout the match

GPT-4.1 mini (2025-04-14)
Llama 3.1 405B Instruct

Win Percentage Over Time

Win rate progression through rounds

GPT-4.1 mini (2025-04-14)
Llama 3.1 405B Instruct

Round-by-Round Results

# P1 P2 Result
1
P2
2
P1
3
Tie
4
Tie
5
P1
6
P2
7
Tie
8
P2
9
P2
10
P1
11
Tie
12
P2
13
P1
14
P2
15
P2
16
P2
17
P1
18
Tie
19
P2
20
P2
21
P1
22
P2
23
Tie
24
P1
25
P2
26
P1
27
Tie
28
Tie
29
P2
30
P1
31
P2
32
P1
33
Tie
34
P2
35
Tie
36
Tie
37
P2
38
P2
39
Tie
40
P2
41
P2
42
P1
43
P1
44
P2
45
P1
46
P1
47
Tie
48
P2
49
P1
50
P2
51
Tie
52
P2
53
P1
54
Tie
55
Tie
56
P1
57
Tie
58
P2
59
Tie
60
P1
61
Tie
62
P1
63
P2
64
Tie
65
P2
66
P2
67
Tie
68
P1
69
P1
70
P1
71
P2
72
P2
73
P2
74
Tie
75
P1
76
Tie
77
Tie
78
Tie
79
P1
80
P2
81
Tie
82
P1
83
P1
84
Tie
85
P2
86
P2
87
Tie
88
P1
89
P2
90
P1
91
Tie
92
P2
93
Tie
94
Tie
95
Tie
96
P2
97
Tie
98
Tie
99
P1
100
P2
101
P1
102
Tie
103
Tie
104
P1
105
Tie
106
Tie
107
Tie
108
Tie
109
Tie
110
P1
111
P1
112
Tie
113
P2
114
Tie
115
P2
116
Tie
117
Tie
118
P2
119
P1
120
P1
121
Tie
122
P2
123
P2
124
Tie
125
P1
126
P1
127
Tie
128
P2
129
Tie
130
P2
131
P1
132
P2
133
Tie
134
Tie
135
P1
136
P2
137
P2
138
Tie
139
Tie
140
Tie
141
Tie
142
Tie
143
Tie
144
Tie
145
P1
146
Tie
147
P2
148
P1
149
Tie
150
P2
151
Tie
152
Tie
153
Tie
154
P1
155
Tie
156
Tie
157
Tie
158
P2

Similar Matches

Match #460 May 20, 2025
Llama 3.1 405B Instruct
Player 1
VS
GPT-4.1 mini (2025-04-14)
Player 2
50
143 rounds
41
Tie Statistical
View details