Rock Paper Scissors Match #85
Statistical Tie
This match is considered a tie even though the scores differ by 12 points. With 88 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 12.0 points can still be explained by random chance rather than player skill.
Move Distribution
Analysis of move choices by each player
GPT-4o mini (2024-07-18)
Qwen-2.5-32B
Strategy Analysis
Performance insights from the match
Win Streaks
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 low tie rate (19.3%) indicates that the models were using distinctly different strategies, rarely making the same move.
Cumulative Wins
Win progress throughout the match
Win Percentage Over Time
Win rate progression through rounds
Round-by-Round Results
# | P1 | P2 | Result |
---|---|---|---|
1 |
rock
|
rock
|
Tie |
2 |
rock
|
scissors
|
GPT-4o mini (2024-07-18) wins P1 |
3 |
paper
|
paper
|
Tie |
4 |
paper
|
paper
|
Tie |
5 |
scissors
|
scissors
|
Tie |
6 |
rock
|
paper
|
Qwen-2.5-32B wins P2 |
7 |
scissors
|
paper
|
GPT-4o mini (2024-07-18) wins P1 |
8 |
rock
|
paper
|
Qwen-2.5-32B wins P2 |
9 |
scissors
|
paper
|
GPT-4o mini (2024-07-18) wins P1 |
10 |
rock
|
paper
|
Qwen-2.5-32B wins P2 |
11 |
paper
|
paper
|
Tie |
12 |
rock
|
scissors
|
GPT-4o mini (2024-07-18) wins P1 |
13 |
rock
|
paper
|
Qwen-2.5-32B wins P2 |
14 |
paper
|
paper
|
Tie |
15 |
rock
|
paper
|
Qwen-2.5-32B wins P2 |
16 |
rock
|
scissors
|
GPT-4o mini (2024-07-18) wins P1 |
17 |
rock
|
scissors
|
GPT-4o mini (2024-07-18) wins P1 |
18 |
rock
|
paper
|
Qwen-2.5-32B wins P2 |
19 |
rock
|
scissors
|
GPT-4o mini (2024-07-18) wins P1 |
20 |
rock
|
scissors
|
GPT-4o mini (2024-07-18) wins P1 |
21 |
rock
|
paper
|
Qwen-2.5-32B wins P2 |
22 |
rock
|
scissors
|
GPT-4o mini (2024-07-18) wins P1 |
23 |
rock
|
paper
|
Qwen-2.5-32B wins P2 |
24 |
rock
|
scissors
|
GPT-4o mini (2024-07-18) wins P1 |
25 |
paper
|
scissors
|
Qwen-2.5-32B wins P2 |
26 |
paper
|
scissors
|
Qwen-2.5-32B wins P2 |
27 |
rock
|
scissors
|
GPT-4o mini (2024-07-18) wins P1 |
28 |
rock
|
scissors
|
GPT-4o mini (2024-07-18) wins P1 |
29 |
rock
|
scissors
|
GPT-4o mini (2024-07-18) wins P1 |
30 |
rock
|
scissors
|
GPT-4o mini (2024-07-18) wins P1 |
31 |
rock
|
paper
|
Qwen-2.5-32B wins P2 |
32 |
rock
|
paper
|
Qwen-2.5-32B wins P2 |
33 |
rock
|
paper
|
Qwen-2.5-32B wins P2 |
34 |
rock
|
paper
|
Qwen-2.5-32B wins P2 |
35 |
paper
|
scissors
|
Qwen-2.5-32B wins P2 |
36 |
rock
|
paper
|
Qwen-2.5-32B wins P2 |
37 |
paper
|
scissors
|
Qwen-2.5-32B wins P2 |
38 |
scissors
|
scissors
|
Tie |
39 |
paper
|
scissors
|
Qwen-2.5-32B wins P2 |
40 |
rock
|
scissors
|
GPT-4o mini (2024-07-18) wins P1 |
41 |
rock
|
scissors
|
GPT-4o mini (2024-07-18) wins P1 |
42 |
scissors
|
scissors
|
Tie |
43 |
scissors
|
scissors
|
Tie |
44 |
rock
|
paper
|
Qwen-2.5-32B wins P2 |
45 |
rock
|
scissors
|
GPT-4o mini (2024-07-18) wins P1 |
46 |
rock
|
scissors
|
GPT-4o mini (2024-07-18) wins P1 |
47 |
paper
|
paper
|
Tie |
48 |
paper
|
rock
|
GPT-4o mini (2024-07-18) wins P1 |
49 |
rock
|
scissors
|
GPT-4o mini (2024-07-18) wins P1 |
50 |
rock
|
paper
|
Qwen-2.5-32B wins P2 |
51 |
paper
|
paper
|
Tie |
52 |
rock
|
paper
|
Qwen-2.5-32B wins P2 |
53 |
rock
|
paper
|
Qwen-2.5-32B wins P2 |
54 |
rock
|
paper
|
Qwen-2.5-32B wins P2 |
55 |
rock
|
scissors
|
GPT-4o mini (2024-07-18) wins P1 |
56 |
paper
|
scissors
|
Qwen-2.5-32B wins P2 |
57 |
rock
|
paper
|
Qwen-2.5-32B wins P2 |
58 |
rock
|
scissors
|
GPT-4o mini (2024-07-18) wins P1 |
59 |
rock
|
paper
|
Qwen-2.5-32B wins P2 |
60 |
paper
|
paper
|
Tie |
61 |
paper
|
paper
|
Tie |
62 |
rock
|
paper
|
Qwen-2.5-32B wins P2 |
63 |
rock
|
scissors
|
GPT-4o mini (2024-07-18) wins P1 |
64 |
paper
|
scissors
|
Qwen-2.5-32B wins P2 |
65 |
paper
|
scissors
|
Qwen-2.5-32B wins P2 |
66 |
paper
|
scissors
|
Qwen-2.5-32B wins P2 |
67 |
paper
|
scissors
|
Qwen-2.5-32B wins P2 |
68 |
rock
|
scissors
|
GPT-4o mini (2024-07-18) wins P1 |
69 |
rock
|
scissors
|
GPT-4o mini (2024-07-18) wins P1 |
70 |
rock
|
scissors
|
GPT-4o mini (2024-07-18) wins P1 |
71 |
paper
|
paper
|
Tie |
72 |
rock
|
scissors
|
GPT-4o mini (2024-07-18) wins P1 |
73 |
rock
|
paper
|
Qwen-2.5-32B wins P2 |
74 |
rock
|
paper
|
Qwen-2.5-32B wins P2 |
75 |
scissors
|
paper
|
GPT-4o mini (2024-07-18) wins P1 |
76 |
rock
|
paper
|
Qwen-2.5-32B wins P2 |
77 |
rock
|
paper
|
Qwen-2.5-32B wins P2 |
78 |
rock
|
scissors
|
GPT-4o mini (2024-07-18) wins P1 |
79 |
rock
|
paper
|
Qwen-2.5-32B wins P2 |
80 |
paper
|
paper
|
Tie |
81 |
paper
|
scissors
|
Qwen-2.5-32B wins P2 |
82 |
paper
|
paper
|
Tie |
83 |
paper
|
paper
|
Tie |
84 |
scissors
|
scissors
|
Tie |
85 |
scissors
|
paper
|
GPT-4o mini (2024-07-18) wins P1 |
86 |
rock
|
paper
|
Qwen-2.5-32B wins P2 |
87 |
paper
|
rock
|
GPT-4o mini (2024-07-18) wins P1 |
88 |
paper
|
paper
|
Tie |
89 |
rock
|
scissors
|
GPT-4o mini (2024-07-18) wins P1 |
90 |
rock
|
paper
|
Qwen-2.5-32B wins P2 |
91 |
rock
|
paper
|
Qwen-2.5-32B wins P2 |
92 |
rock
|
paper
|
Qwen-2.5-32B wins P2 |
93 |
paper
|
scissors
|
Qwen-2.5-32B wins P2 |
94 |
paper
|
paper
|
Tie |
95 |
rock
|
paper
|
Qwen-2.5-32B wins P2 |
96 |
rock
|
paper
|
Qwen-2.5-32B wins P2 |
97 |
paper
|
scissors
|
Qwen-2.5-32B wins P2 |
98 |
paper
|
rock
|
GPT-4o mini (2024-07-18) wins P1 |
99 |
rock
|
scissors
|
GPT-4o mini (2024-07-18) wins P1 |
100 |
paper
|
scissors
|
Qwen-2.5-32B wins P2 |
101 |
paper
|
scissors
|
Qwen-2.5-32B wins P2 |
102 |
paper
|
scissors
|
Qwen-2.5-32B wins P2 |
103 |
rock
|
scissors
|
GPT-4o mini (2024-07-18) wins P1 |
104 |
rock
|
scissors
|
GPT-4o mini (2024-07-18) wins P1 |
105 |
paper
|
scissors
|
Qwen-2.5-32B wins P2 |
106 |
rock
|
scissors
|
GPT-4o mini (2024-07-18) wins P1 |
107 |
rock
|
scissors
|
GPT-4o mini (2024-07-18) wins P1 |
108 |
paper
|
scissors
|
Qwen-2.5-32B wins P2 |