Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Social Deduction Game Gameplay on Avalon
Loading...
78.5
Good Side Win Rate
Ours + Strategist
70.18
72.34
74.5
76.66
Oct 10, 2025
Good Side Win Rate
Evil Side Win Rate
Overall Win Rate
Updated 4d ago
Evaluation Results
Method
Method
Links
Good Side Win Rate
Evil Side Win Rate
Overall Win Rate
Ours + Strategist
Backend LLM=Gemini-2.5...
2025.10
78.5
35.2
61.3
Strategist
Backend LLM=Gemini-2.5...
2025.10
77.6
27
57.4
ReCon
Backend LLM=Gemini-2.5...
2025.10
73.2
19.5
51.6
Ours + ReAct
Backend LLM=Gemini-2.5...
2025.10
73.1
30.9
56.4
LASI
Backend LLM=Gemini-2.5...
2025.10
71.8
25
53
ReAct
Backend LLM=Gemini-2.5...
2025.10
70.5
16
48.7
Feedback
Search any
task
Search any
task