Chess
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
chess
99.47F1 Score
30
Chess (Exploratory Learning Phase)
24.11Blunder Rate
16
chess
93.22ROC-AUC
14
chess
1.86PR-AUC
14
chess
85.4Accuracy
12
Chess Skill: beginner, intermediate, advanced
100Accuracy
10
Chess Specialists: opening, midgame, endgame, late-endgame
64.4Accuracy
10
chess (test)
85F1 Score
8
Chess 1,002 disjoint positions
-243Mean Evaluation (cp)
5
Chess (8, 8) (test)
84.3Accuracy
4
chess
99.47F1 Score
3
Chess (test)
82.42Macro F1-score
3
Chess
98Coverage
3
Chess
6.12Runtime
2
Chess Match vs Stockfish 100 games
25Win Rate
2
Chess
6.12Construction Time
1
Chess O3
126,516,521Extracted Instructions
1
Chess O2
1,905,184Extracted Instructions Count
1
Chess O0
8,568,798Extracted Instructions Count
1