Deductive Reasoning on BBH Ded.
92.5AccuracyBranching
Evaluation Results
| Method | Links | |
|---|---|---|
| BranchingModel=Phi-4-reasoning-plus (13B)2026.04 | 92.5 | |
| Beam Search (BL)Model=Phi-4-reasoning-plus (13B)2026.04 | 91.3 | |
| Beam Search (BL)Model=Gemma-3-12b-it2026.04 | 89.2 | |
| SteeringModel=Phi-4-reasoning-plus (13B)2026.04 | 88.7 | |
| SteeringModel=Gemma-3-12b-it2026.04 | 87.8 | |
| Greedy (BL)Model=Gemma-3-12b-it2026.04 | 87.5 | |
| BranchingModel=Gemma-3-12b-it2026.04 | 87.4 | |
| TTPOModel=Gemma-3-12b-it2026.04 | 86.4 | |
| TTPOModel=Phi-4-reasoning-plus (13B)2026.04 | 86.4 | |
| Beam SearchModel=Gemma-3-4b-it, beam size=52026.04 | 77 | |
| Beam Search (BL)Model=Gemma-3-4b-it2026.04 | 77 | |
| TTPOModel=Gemma-3-4b-it2026.04 | 75.9 | |
| TTPOModel=Gemma-3-4b-it2026.04 | 75.9 | |
| Self-ConsistencyModel=Gemma-3-4b-it, n=52026.04 | 75.5 | |
| SteeringModel=Gemma-3-4b-it2026.04 | 75.5 | |
| GreedyModel=Gemma-3-4b-it2026.04 | 75.3 | |
| Greedy (BL)Model=Gemma-3-4b-it2026.04 | 75.3 | |
| BranchingModel=Gemma-3-4b-it2026.04 | 74.7 | |
| Beam SearchModel=Phi-4-mini-instruct (4B), beam size=52026.04 | 73.8 | |
| Beam Search (BL)Model=Phi-4-mini-instruct (4B)2026.04 | 73.8 | |
| Self-ConsistencyModel=Phi-4-mini-instruct (4B), n=52026.04 | 73.6 | |
| Greedy (BL)Model=Phi-4-reasoning-plus (13B)2026.04 | 70.2 | |
| BranchingModel=Phi-4-mini-instruct (4B)2026.04 | 69.1 | |
| BranchingModel=Phi-4-mini-instruct (4B)2026.04 | 69.1 | |
| SteeringModel=Phi-4-mini-instruct (4B)2026.04 | 68.8 | |
| GreedyModel=Phi-4-mini-instruct (4B)2026.04 | 67.3 | |
| Greedy (BL)Model=Phi-4-mini-instruct (4B)2026.04 | 67.3 | |
| TTPOModel=Phi-4-mini-instruct (4B)2026.04 | 67.2 |