Strategy Games on Lichess
54.5PerformanceGround Truth
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| Ground TruthStudent=OLMo2-13B2026.05 | 54.5 | — | |
| Ground TruthStudent=OLMo2-7B2026.05 | 52.9 | — | |
| NTFTeacher=Qwen3-0.6B, Student=Qwen3-14B2026.05 | 44.1 | 110.4 | |
| NTFTeacher=OLMo2-1B, Student=OLMo2-13B2026.05 | 41.5 | 76.1 | |
| NTFTeacher=OLMo2-1B, Student=OLMo2-7B2026.05 | 41.2 | 77.9 | |
| I-ConfidenceTeacher=OLMo2-1B, Student=OLMo2-13B2026.05 | 40.7 | 74.7 | |
| I-ConfidenceTeacher=OLMo2-1B, Student=OLMo2-7B2026.05 | 39.9 | 75.4 | |
| Ground TruthStudent=Qwen3-14B2026.05 | 39.9 | — | |
| V-ConfidenceTeacher=OLMo2-1B, Student=OLMo2-13B2026.05 | 38.7 | 71 | |
| NaiveTeacher=OLMo2-1B, Student=OLMo2-13B2026.05 | 38.3 | 70.3 | |
| NaiveTeacher=Qwen3-0.6B, Student=Qwen3-14B2026.05 | 38.1 | 95.5 | |
| NTFTeacher=Qwen3-0.6B, Student=Qwen3-8B2026.05 | 38 | 102.9 | |
| V-ConfidenceTeacher=OLMo2-1B, Student=OLMo2-7B2026.05 | 37.7 | 71.3 | |
| Ground TruthStudent=OLMo2-1B2026.05 | 37.7 | — | |
| I-ConfidenceTeacher=Qwen3-0.6B, Student=Qwen3-14B2026.05 | 37.5 | 94 | |
| NTFTeacher=OLMo2-1B, Student=OLMo2-1B2026.05 | 37.4 | 99.2 | |
| I-ConfidenceTeacher=OLMo2-1B, Student=OLMo2-1B2026.05 | 37.1 | 98.4 | |
| NaiveTeacher=OLMo2-1B, Student=OLMo2-7B2026.05 | 37 | 69.9 | |
| Ground TruthStudent=Qwen3-8B2026.05 | 37 | — | |
| I-ConfidenceTeacher=Qwen3-0.6B, Student=Qwen3-4B2026.05 | 36.9 | 101.7 | |
| I-ConfidenceTeacher=Qwen3-0.6B, Student=Qwen3-8B2026.05 | 36.3 | 98.1 | |
| Ground TruthStudent=Qwen3-4B2026.05 | 36.3 | — | |
| NTFTeacher=Qwen3-0.6B, Student=Qwen3-4B2026.05 | 35.4 | 97.6 | |
| V-ConfidenceTeacher=OLMo2-1B, Student=OLMo2-1B2026.05 | 35.2 | 93.4 | |
| NaiveTeacher=OLMo2-1B, Student=OLMo2-1B2026.05 | 34.7 | 92 | |
| NaiveTeacher=Qwen3-0.6B, Student=Qwen3-8B2026.05 | 33.7 | 91.1 | |
| V-ConfidenceTeacher=Qwen3-0.6B, Student=Qwen3-14B2026.05 | 33.4 | 83.7 | |
| V-ConfidenceTeacher=Qwen3-0.6B, Student=Qwen3-4B2026.05 | 31.8 | 87.6 | |
| V-ConfidenceTeacher=Qwen3-0.6B, Student=Qwen3-8B2026.05 | 31.8 | 85.9 | |
| NaiveTeacher=Qwen3-0.6B, Student=Qwen3-4B2026.05 | 27 | 74.4 | |
| NTFTeacher=Qwen3-0.6B, Student=Qwen3-1.7B2026.05 | 25.4 | 110.5 | |
| I-ConfidenceTeacher=Qwen3-0.6B, Student=Qwen3-1.7B2026.05 | 23 | 100 | |
| Ground TruthStudent=Qwen3-1.7B2026.05 | 23 | — | |
| NaiveTeacher=Qwen3-0.6B, Student=Qwen3-1.7B2026.05 | 22.1 | 96.1 | |
| V-ConfidenceTeacher=Qwen3-0.6B, Student=Qwen3-1.7B2026.05 | 17.9 | 77.8 | |
| NTFTeacher=Qwen3-0.6B, Student=Qwen3-0.6B2026.05 | 15.5 | 104.4 | |
| Ground TruthStudent=Qwen3-0.6B2026.05 | 14.9 | — | |
| I-ConfidenceTeacher=Qwen3-0.6B, Student=Qwen3-0.6B2026.05 | 11.5 | 77.2 | |
| NaiveTeacher=Qwen3-0.6B, Student=Qwen3-0.6B2026.05 | 10.6 | 71.1 | |
| V-ConfidenceTeacher=Qwen3-0.6B, Student=Qwen3-0.6B2026.05 | 7.3 | 49 |