Planning and Reasoning on Sudoku
99.4AccuracyDTM
Evaluation Results
| Method | Links | |
|---|---|---|
| DTMSeq Len=512, Shot count=3-SHOT2026.04 | 99.4 | |
| DTMSeq Len=256, Shot count=3-SHOT2026.04 | 99.2 | |
| SPGSeq Len=256, Shot count=3-SHOT2026.04 | 94 | |
| SPGSeq Len=512, Shot count=3-SHOT2026.04 | 93.1 | |
| UNIGRPOSeq Len=256, Shot count=3-SHOT2026.04 | 67 | |
| UNIGRPOSeq Len=512, Shot count=3-SHOT2026.04 | 62.9 | |
| D1Seq Len=256, Shot count=3-SHOT2026.04 | 32.5 | |
| WD1Seq Len=256, Shot count=3-SHOT2026.04 | 32.1 | |
| D1Seq Len=512, Shot count=3-SHOT2026.04 | 29.3 | |
| LLADA-1.5Seq Len=512, Shot count=3-SHOT2026.04 | 29 | |
| LLADA-8B-INST.Seq Len=256, Shot count=3-SHOT2026.04 | 27.7 | |
| LLADA-1.5Seq Len=256, Shot count=3-SHOT2026.04 | 26.9 | |
| LLADA-8B-INST.Seq Len=512, Shot count=3-SHOT2026.04 | 26.2 | |
| WD1Seq Len=512, Shot count=3-SHOT2026.04 | 22.5 |