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

Gaming Content

Benchmarks

Task NameDataset NameSOTA ResultTrend
Human Pairwise ComparisonGaming Content N=60 samples (Unfamiliar Games)
Win %86.7
8
Human Pairwise ComparisonGaming Content Familiar Games N=60 samples
Win Rate83.3
8
Showing 2 of 2 rows