Math Reasoning on MATH 500 (Accuracy %)
30.8Accuracy (MATH 500)Dream 7B-Instruct (Top Probability + Suffix-Anchored Confidence Modulation)
Evaluation Results
| Method | Links | |
|---|---|---|
| Dream 7B-Instruct (Top Probability + Suffix-Anchored Confidence Modulation)Model=Dream 7B-Instruct, Decoding Strategy=Top Probability, Suffix Anchor=true, Confidence Modulation=true2026.05 | 30.8 | |
| LLaDA 8B-Instruct (Top Probability + Suffix-Anchored Confidence Modulation)Model=LLaDA 8B-Instruct, Decoding Strategy=Top Probability, Suffix Anchor=true, Confidence Modulation=true2026.05 | 29 | |
| Dream 7B-Instruct (Top Margin + Suffix-Anchored Confidence Modulation)Model=Dream 7B-Instruct, Decoding Strategy=Top Margin, Suffix Anchor=true, Confidence Modulation=true2026.05 | 28.6 | |
| LLaDA 8B-Instruct (Top Margin + Suffix-Anchored Confidence Modulation)Model=LLaDA 8B-Instruct, Decoding Strategy=Top Margin, Suffix Anchor=true, Confidence Modulation=true2026.05 | 25.4 | |
| Dream 7B-Instruct (Top Margin + Suffix Anchor)Model=Dream 7B-Instruct, Decoding Strategy=Top Margin, Suffix Anchor=true, Confidence Modulation=false2026.05 | 23.6 | |
| Dream 7B-Instruct (Top Probability + Suffix Anchor)Model=Dream 7B-Instruct, Decoding Strategy=Top Probability, Suffix Anchor=true, Confidence Modulation=false2026.05 | 23.2 | |
| LLaDA 8B-Instruct (Top Margin + Suffix Anchor)Model=LLaDA 8B-Instruct, Decoding Strategy=Top Margin, Suffix Anchor=true, Confidence Modulation=false2026.05 | 22.4 | |
| LLaDA 8B-Instruct (Top Probability + Suffix Anchor)Model=LLaDA 8B-Instruct, Decoding Strategy=Top Probability, Suffix Anchor=true, Confidence Modulation=false2026.05 | 21.8 | |
| LLaDA 8B-Instruct (Random)Model=LLaDA 8B-Instruct, Decoding Strategy=Random, Suffix Anchor=false, Confidence Modulation=false2026.05 | 18 | |
| LLaDA 8B-Instruct (Top Margin)Model=LLaDA 8B-Instruct, Decoding Strategy=Top Margin, Suffix Anchor=false, Confidence Modulation=false2026.05 | 16.2 | |
| LLaDA 8B-Instruct (Top Probability)Model=LLaDA 8B-Instruct, Decoding Strategy=Top Probability, Suffix Anchor=false, Confidence Modulation=false2026.05 | 14.6 | |
| Dream 7B-Instruct (Top Margin)Model=Dream 7B-Instruct, Decoding Strategy=Top Margin, Suffix Anchor=false, Confidence Modulation=false2026.05 | 13.4 | |
| Dream 7B-Instruct (Top Probability)Model=Dream 7B-Instruct, Decoding Strategy=Top Probability, Suffix Anchor=false, Confidence Modulation=false2026.05 | 12.4 | |
| Dream 7B-Instruct (Random)Model=Dream 7B-Instruct, Decoding Strategy=Random, Suffix Anchor=false, Confidence Modulation=false2026.05 | 6.6 |