List your company

Mathematical Reasoning on Stream Mostly-Hard

16.6AccuracyOracle
-0.6643.8188.312.782Jun 2, 2026

Evaluation results

MethodLinks
OracleBudget=20482026.0616.6
PredictorBudget=20482026.0612.8
CLEAR (Heaur.)Budget=20482026.0612.8
CLEAR (Auction)Budget=20482026.0612.8
CLEAR (Lambert)Budget=20482026.0612.8
OracleBudget=10242026.0612.8
TALE-EPBudget=20482026.0612
UniformBudget=20482026.0611.4
OracleBudget=5122026.0611.4
OracleBudget=2562026.069.6
TALE-EPBudget=9.22026.069.2
PredictorBudget=10242026.068.2
CLEAR (Heaur.)Budget=10242026.068.2
CLEAR (Auction)Budget=10242026.068.2
CLEAR (Lambert)Budget=10242026.068.2
CLEAR (Heaur.)Budget=5122026.067.2
UniformBudget=10242026.066.8
CLEAR (Lambert)Budget=5122026.066.8
CLEAR (Auction)Budget=5122026.066.6
CLEAR (Lambert)Budget=2562026.066.2
CLEAR (Auction)Budget=2562026.066
TALE-EPBudget=5122026.065.8
UniformBudget=5122026.065
TALE-EPBudget=2562026.064.2
CLEAR (Heaur.)Budget=2562026.064
PredictorBudget=5122026.061.6
UniformBudget=2562026.061
PredictorBudget=2562026.060