Calibration
Video-MME (w/o subtitle) → MMMU
MMMU is estimated from Video-MME (w/o subtitle) with a linear curve fitted on 7 models measured on both: y = 1.1216·x + -0.1003, R² = 0.97, cross-validated error 1.1 pp. It is used for 0 estimates.
MMMU is estimated from Video-MME (w/o subtitle) with a linear curve fitted on 7 models measured on both: y = 1.1216·x + -0.1003, R² = 0.97, cross-validated error 1.1 pp. It is used for 0 estimates.