Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Avalon

Benchmarks

Task NameDataset NameSOTA ResultTrend
Solving Hidden-Role GamesAvalon 5 Players
Equilibrium Value731
7
Social Deduction Game GameplayAvalon
Good Side Win Rate78.5
6
Solving Hidden-Role GamesAvalon 6 Players
Equilibrium Value6,543
6
Multi-agent Game PlayingAvalon Homogeneous Teams (test)
Win Rate (vs. Rand)95
5
Showing 4 of 4 rows