Combinatorial Reasoning on ZebraLogic (mc_mode, Rows/Cols <= 4)
73.73Average Score @64No pruning (Baseline)
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| No pruning (Baseline)Model=DS-Qwen-2.5-7B2026.04 | 73.73 | — | — | |
| STOPModel=DS-Qwen-2.5-7B2026.04 | — | 77.23 | 3.5 |
Loading the SOTA2 catalog…