List your company
ResearchFormerly WizWand

Logical Planning on Sudoku (test)

91.7AccuracyGDSD w/ TLC
-1.48422.70846.971.092May 28, 2026
Updated 5mo ago

Evaluation results

MethodLinks
GDSD w/ TLCSeq Len=512, Zero-shot=true, Base Model=Dream-7B-Instruct2026.0591.7
GDSD w/ TLCSeq Len=Avg., Zero-shot=true, Base Model=Dream-7B-Instruct2026.0591.4
GDSD w/ TLCSeq Len=256, Zero-shot=true, Base Model=Dream-7B-Instruct2026.0591.3
GDSD w/ TLCSeq Len=128, Zero-shot=true, Base Model=Dream-7B-Instruct2026.0591.1
GDSDSeq Len=128, Zero-shot=true, Base Model=Dream-7B-Instruct2026.0582.3
GDSDSeq Len=256, Zero-shot=true, Base Model=Dream-7B-Instruct2026.0582.2
GDSDSeq Len=Avg., Zero-shot=true, Base Model=Dream-7B-Instruct2026.0581.3
GDSDSeq Len=512, Zero-shot=true, Base Model=Dream-7B-Instruct2026.0579.3
ESPOSeq Len=256, Zero-shot=true, Base Model=Dream-7B-Instruct2026.0572.3
ESPOSeq Len=Avg., Zero-shot=true, Base Model=Dream-7B-Instruct2026.0571.8
ESPOSeq Len=128, Zero-shot=true, Base Model=Dream-7B-Instruct2026.0571.7
ESPOSeq Len=512, Zero-shot=true, Base Model=Dream-7B-Instruct2026.0571.3
diffu-GRPO (d1)Seq Len=256, Zero-shot=true, Base Model=Dream-7B-Instruct2026.0569.7
diffu-GRPO (d1)Seq Len=128, Zero-shot=true, Base Model=Dream-7B-Instruct2026.0564.4
diffu-GRPO (d1)Seq Len=Avg., Zero-shot=true, Base Model=Dream-7B-Instruct2026.0561.7
diffu-GRPO (d1)Seq Len=512, Zero-shot=true, Base Model=Dream-7B-Instruct2026.0551.1
wd1Seq Len=256, Zero-shot=true, Base Model=Dream-7B-Instruct2026.0539.2
wd1Seq Len=Avg., Zero-shot=true, Base Model=Dream-7B-Instruct2026.0533
wd1Seq Len=512, Zero-shot=true, Base Model=Dream-7B-Instruct2026.0530.3
wd1Seq Len=128, Zero-shot=true, Base Model=Dream-7B-Instruct2026.0529.5
Dream-7BSeq Len=512, Zero-shot=true, Base Model=Dream-7B-Instruct2026.0514
Dream-7BSeq Len=128, Zero-shot=true, Base Model=Dream-7B-Instruct2026.059.3
Dream-7BSeq Len=Avg., Zero-shot=true, Base Model=Dream-7B-Instruct2026.058.5
Dream-7BSeq Len=256, Zero-shot=true, Base Model=Dream-7B-Instruct2026.052.1