List your company
ResearchFormerly WizWand

Logical Planning on Countdown (test)

84.8AccuracyGDSD w/ TLC
4.7225.5146.367.09May 28, 2026
Updated 5mo ago

Evaluation results

MethodLinks
GDSD w/ TLCSeq Len=512, Zero-shot=true, Base Model=Dream-7B-Instruct2026.0584.8
GDSD w/ TLCSeq Len=Avg., Zero-shot=true, Base Model=Dream-7B-Instruct2026.0583.5
GDSD w/ TLCSeq Len=128, Zero-shot=true, Base Model=Dream-7B-Instruct2026.0583.2
GDSD w/ TLCSeq Len=256, Zero-shot=true, Base Model=Dream-7B-Instruct2026.0582.4
GDSDSeq Len=128, Zero-shot=true, Base Model=Dream-7B-Instruct2026.0570.3
ESPOSeq Len=128, Zero-shot=true, Base Model=Dream-7B-Instruct2026.0568.8
GDSDSeq Len=256, Zero-shot=true, Base Model=Dream-7B-Instruct2026.0568.4
GDSDSeq Len=Avg., Zero-shot=true, Base Model=Dream-7B-Instruct2026.0567.5
ESPOSeq Len=256, Zero-shot=true, Base Model=Dream-7B-Instruct2026.0566.8
ESPOSeq Len=Avg., Zero-shot=true, Base Model=Dream-7B-Instruct2026.0566.8
ESPOSeq Len=512, Zero-shot=true, Base Model=Dream-7B-Instruct2026.0564.8
GDSDSeq Len=512, Zero-shot=true, Base Model=Dream-7B-Instruct2026.0563.7
wd1Seq Len=512, Zero-shot=true, Base Model=Dream-7B-Instruct2026.0542.2
wd1Seq Len=256, Zero-shot=true, Base Model=Dream-7B-Instruct2026.0537.9
diffu-GRPO (d1)Seq Len=512, Zero-shot=true, Base Model=Dream-7B-Instruct2026.0537.5
wd1Seq Len=Avg., Zero-shot=true, Base Model=Dream-7B-Instruct2026.0536.3
diffu-GRPO (d1)Seq Len=Avg., Zero-shot=true, Base Model=Dream-7B-Instruct2026.0530.8
wd1Seq Len=128, Zero-shot=true, Base Model=Dream-7B-Instruct2026.0528.9
diffu-GRPO (d1)Seq Len=256, Zero-shot=true, Base Model=Dream-7B-Instruct2026.0527.7
diffu-GRPO (d1)Seq Len=128, Zero-shot=true, Base Model=Dream-7B-Instruct2026.0527.3
Dream-7BSeq Len=512, Zero-shot=true, Base Model=Dream-7B-Instruct2026.0517.4
Dream-7BSeq Len=Avg., Zero-shot=true, Base Model=Dream-7B-Instruct2026.0511.2
Dream-7BSeq Len=128, Zero-shot=true, Base Model=Dream-7B-Instruct2026.058.5
Dream-7BSeq Len=256, Zero-shot=true, Base Model=Dream-7B-Instruct2026.057.8