List your company

Mathematical Reasoning on GSM8K (accuracy, average accuracy)

86.4AccuracyGDSD
70.69674.77378.8582.927May 28, 2026

Evaluation results

MethodLinks
GDSDSequence Length=2562026.0586.4—
GDSDSequence Length=5122026.0586—
GDSD w/ TLCSequence Length=2562026.0585.6—
DMPOSequence Length=5122026.0585.2—
SPGSequence Length=2562026.0585.1—
GDSD w/ TLCSequence Length=5122026.0585—
SPGSequence Length=5122026.0584.9—
GDSDSequence Length=1282026.0583.9—
ESPOSequence Length=5122026.0583—
SPGSequence Length=1282026.0582.8—
UniGRPOSequence Length=5122026.0582.7—
UniGRPOSequence Length=2562026.0582.5—
ESPOSequence Length=2562026.0582.5—
DMPOSequence Length=2562026.0582.4—
wd1Sequence Length=5122026.0582.3—
ESPOSequence Length=1282026.0581.6—
GDSD w/ TLCSequence Length=1282026.0581.3—
diffu-GRPO (d1)Sequence Length=5122026.0581.2—
wd1Sequence Length=2562026.0580.8—
LLaDA-8BSequence Length=5122026.0580.2—
diffu-GRPO (d1)Sequence Length=2562026.0578.1—
wd1Sequence Length=1282026.0577.2—
LLaDA-8BSequence Length=2562026.0576.2—
UniGRPOSequence Length=1282026.0574.9—
DMPOSequence Length=1282026.0574.8—
diffu-GRPO (d1)Sequence Length=1282026.0574.6—
LLaDA-8BSequence Length=1282026.0571.3—
diffu-GRPO (d1)Sequence Length=Average2026.05—78
DMPOSequence Length=Average2026.05—80.8
ESPOSequence Length=Average2026.05—82.4
GDSDSequence Length=Average2026.05—85.4
GDSD w/ TLCSequence Length=Average2026.05—84
LLaDA-8BSequence Length=Average2026.05—75.9
SPGSequence Length=Average2026.05—84.2
UniGRPOSequence Length=Average2026.05—80
wd1Sequence Length=Average2026.05—80.1