First-move Accuracy on Chess Puzzle Themes (test)
61.1Advanced Pawn AccuracyC1-4B
Evaluation Results
| Method | Links | |||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| C1-4Bconfidence_interval=99% Wilson interval2026.05 | 61.1 | 61.1 | 76.9 | 54.7 | 57.9 | 38.9 | 45.3 | 51.6 | 38.9 | 61.1 | 61.1 | 54.7 | 32.6 | 51.6 | 64.2 | 57.9 | 51.6 | 13.6 | 51.6 | 70.5 | 53.6 | |
| KinGPT-Chimeraconfidence_interval=99% Wilson interval2026.05 | 60.3 | 63.1 | 91.3 | 64.1 | 60.3 | 71.6 | 60.3 | 72.5 | 65 | 79.1 | 84.7 | 82.8 | 61.3 | 69.7 | 68.8 | 55.6 | 73.4 | 48.1 | 73.4 | 77.2 | 70.3 |