List your company

Commonsense Reasoning on StrategyQA (Accuracy (%))

76.13Accuracy (%)Dream 7B-Instruct (Top Margin + Suffix-Anchored Confidence Modulation)
17.390832.640447.8963.1396May 27, 2026May 28, 2026

Evaluation results

MethodLinks
Dream 7B-Instruct (Top Margin + Suffix-Anchored Confidence Modulation)Model=Dream 7B-Instruct, Decoding Strategy=Top Margin, Suffix Anchor=true, Confidence Modulation=true2026.0576.13
Dream 7B-Instruct (Top Margin + Suffix Anchor)Model=Dream 7B-Instruct, Decoding Strategy=Top Margin, Suffix Anchor=true, Confidence Modulation=false2026.0575.98
Dream 7B-Instruct (Top Probability + Suffix-Anchored Confidence Modulation)Model=Dream 7B-Instruct, Decoding Strategy=Top Probability, Suffix Anchor=true, Confidence Modulation=true2026.0575.4
Dream 7B-Instruct (Top Probability + Suffix Anchor)Model=Dream 7B-Instruct, Decoding Strategy=Top Probability, Suffix Anchor=true, Confidence Modulation=false2026.0574.24
VanillaBackbone=Mistral-7B-Instruct2026.0573.6
COFTBackbone=Mistral-7B-Instruct2026.0573.6
DT-CD⋆Backbone=Mistral-7B-Instruct2026.0573.5
SDDBackbone=Mistral-7B-Instruct2026.0573
DExpertsBackbone=Mistral-7B-Instruct2026.0572.8
VanillaBackbone=LLaMA-2-13B2026.0571.2
COFTBackbone=LLaMA-2-13B2026.0571.1
DT-CD⋆Backbone=LLaMA-2-13B2026.0571
SDDBackbone=LLaMA-2-13B2026.0570.5
LLaDA 8B-Instruct (Top Probability + Suffix-Anchored Confidence Modulation)Model=LLaDA 8B-Instruct, Decoding Strategy=Top Probability, Suffix Anchor=true, Confidence Modulation=true2026.0570.45
DExpertsBackbone=LLaMA-2-13B2026.0570.3
Dream 7B-Instruct (Random)Model=Dream 7B-Instruct, Decoding Strategy=Random, Suffix Anchor=false, Confidence Modulation=false2026.0569.43
LLaDA 8B-Instruct (Top Margin + Suffix-Anchored Confidence Modulation)Model=LLaDA 8B-Instruct, Decoding Strategy=Top Margin, Suffix Anchor=true, Confidence Modulation=true2026.0568.12
LLaDA 8B-Instruct (Top Probability + Suffix Anchor)Model=LLaDA 8B-Instruct, Decoding Strategy=Top Probability, Suffix Anchor=true, Confidence Modulation=false2026.0566.52
LLaDA 8B-Instruct (Top Margin + Suffix Anchor)Model=LLaDA 8B-Instruct, Decoding Strategy=Top Margin, Suffix Anchor=true, Confidence Modulation=false2026.0566.08
Dream 7B-Instruct (Top Margin)Model=Dream 7B-Instruct, Decoding Strategy=Top Margin, Suffix Anchor=false, Confidence Modulation=false2026.0562.45
LLaDA 8B-Instruct (Random)Model=LLaDA 8B-Instruct, Decoding Strategy=Random, Suffix Anchor=false, Confidence Modulation=false2026.0558.81
Dream 7B-Instruct (Top Probability)Model=Dream 7B-Instruct, Decoding Strategy=Top Probability, Suffix Anchor=false, Confidence Modulation=false2026.0556.91
LLaDA 8B-Instruct (Top Margin)Model=LLaDA 8B-Instruct, Decoding Strategy=Top Margin, Suffix Anchor=false, Confidence Modulation=false2026.0528.53
LLaDA 8B-Instruct (Top Probability)Model=LLaDA 8B-Instruct, Decoding Strategy=Top Probability, Suffix Anchor=false, Confidence Modulation=false2026.0519.65