Average

Average (BCI-IV-2a, PhysionetMI, SEED-IV)

6

Average all datasets

6

Average Strawberry and PFuji-Size

6

Average across benchmarks

6

Average All Datasets Harmonic Mean

6

Average All Datasets, Low-End Target

6

Average All Datasets, High-End Source

6

Average

6

Average over 5 datasets (test)

6

Average (AVG)

6

Average MATH500, MBPP, Text-to-SQL, QuaLITY

6

Average (Scannet, DL3DV, DTU)

6

Average (test)

6

Average (BDD, MV, ACDC, DZ) (val)

6

Average 494 images (test)

6

Average 11 datasets

5

Average ScanNet++, TUM RGB-D, KITTI

5

Average

5

Average Math500 AIME24 AIME25 GPQA

5

Average All 7 Datasets

5

Average (IEMOCAP, MELD, RAVDESS, CASIA, CAFE, RESD)

5

Average of 5 datasets

5

Average (MuSiQue, 2Wiki, MoreHopQA, FRAMES)

5

Average Hybrid-weather

5

Average

5