List your company
ResearchFormerly WizWand

Mathematical Reasoning on Balanced Stream

26AccuracyOracle
-0.4166.44213.320.158Jun 2, 2026
Updated 5mo ago

Evaluation results

MethodLinks
OracleBudget=20482026.0626
OracleBudget=10242026.0623.6
PredictorBudget=20482026.0622.8
CLEAR (Heaur.)Budget=20482026.0622.8
CLEAR (Auction)Budget=20482026.0622.8
CLEAR (Lambert)Budget=20482026.0622.8
TALE-EPBudget=20482026.0622.2
UniformBudget=20482026.0621.6
OracleBudget=5122026.0621.6
OracleBudget=2562026.0619
PredictorBudget=10242026.0618.8
CLEAR (Heaur.)Budget=10242026.0618.8
CLEAR (Auction)Budget=10242026.0618.8
CLEAR (Lambert)Budget=10242026.0618.8
UniformBudget=10242026.0617.4
CLEAR (Heaur.)Budget=5122026.0617
CLEAR (Lambert)Budget=5122026.0616.4
TALE-EPBudget=10242026.0616
CLEAR (Auction)Budget=5122026.0615.6
CLEAR (Lambert)Budget=2562026.0614.6
CLEAR (Auction)Budget=2562026.0614.2
UniformBudget=5122026.0612.4
CLEAR (Heaur.)Budget=2562026.0611
TALE-EPBudget=5122026.066.8
PredictorBudget=5122026.064.6
TALE-EPBudget=2562026.063.8
UniformBudget=2562026.063
PredictorBudget=2562026.060.6