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

Goofspiel

Benchmarks

Task NameDataset NameSOTA ResultTrend
Two-Player Zero-Sum Game SolvingGoofspiel 13 cards
Estimated PE73.9
112
Game PlayingGoofspiel Standard Benchmarks (test)
Exploitability0.007
8
Game PlayingControl Goofspiel (test)
Exploitability0.105
4
Multi-agent Game PlayingGoofspiel 8 point cards
Metric-
0
Showing 4 of 4 rows