Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Mastermind

Benchmarks

Task NameDataset NameSOTA ResultTrend
Strategic Game PlayingMastermind Extreme
Average Return0.356
9
Strategic Game PlayingMastermind Hard
Average Return0.463
9
Experience ReuseMastermind Qwen3-32B agent
Experience Reuse Rate87.5
6
Experience ReuseMastermind Gemma-3-4B agent
Experience Reuse Rate85
6
Experience ReuseMastermind Extreme v0
Experience Reuse Rate90
6
Experience ReuseMastermind Hard v0
Experience Reuse Rate82.5
6
Experience ReuseMastermind v0
Reuse Rate92.5
6
Showing 7 of 7 rows