Calibration
MMAnswerBench → AIME26
AIME26 is estimated from MMAnswerBench with a linear curve fitted on 10 models measured on both: y = 0.5005·x + 0.5359, R² = 0.87, cross-validated error 0.7 pp. It is used for 0 estimates.
AIME26 is estimated from MMAnswerBench with a linear curve fitted on 10 models measured on both: y = 0.5005·x + 0.5359, R² = 0.87, cross-validated error 0.7 pp. It is used for 0 estimates.