List your company
ResearchFormerly WizWand

Mathematical Reasoning on Mostly-Easy Stream

49.8AccuracyOracle
-0.1212.8425.838.76Jun 2, 2026
Updated 4mo ago

Evaluation results

MethodLinks
OracleBudget=10242026.0649.8
OracleBudget=20482026.0649.8
UniformBudget=20482026.0649
PredictorBudget=20482026.0649
CLEAR (Heaur.)Budget=20482026.0649
CLEAR (Auction)Budget=20482026.0649
CLEAR (Lambert)Budget=20482026.0649
OracleBudget=5122026.0648.4
CLEAR (Lambert)Budget=10242026.0647.6
PredictorBudget=10242026.0646
CLEAR (Heaur.)Budget=10242026.0646
CLEAR (Auction)Budget=10242026.0646
UniformBudget=10242026.0645.6
OracleBudget=2562026.0642.2
CLEAR (Lambert)Budget=5122026.0640.4
TALE-EPBudget=20482026.0639.8
CLEAR (Auction)Budget=5122026.0639.2
CLEAR (Heaur.)Budget=5122026.0637.8
UniformBudget=5122026.0633.8
CLEAR (Lambert)Budget=2562026.0633
CLEAR (Auction)Budget=2562026.0632.8
CLEAR (Heaur.)Budget=2562026.0631.6
TALE-EPBudget=10242026.0622.4
PredictorBudget=5122026.0617.6
TALE-EPBudget=5122026.0610.8
UniformBudget=2562026.069
TALE-EPBudget=2562026.067.2
PredictorBudget=2562026.061.8