List your company

Multimodal QA on SEEDBench (test)

33.7SEEDBench ScorePivotMerge
7.90814.60421.327.996Apr 18, 2026

Evaluation results

MethodLinks
PivotMergePartitioning=Clustering2026.0433.7
TSV-MPartitioning=Clustering2026.0432
CC12M Split 5Partitioning=Clustering2026.0430.6
TIES MergingPartitioning=Clustering2026.0428.9
MetaGPTPartitioning=Clustering2026.0427.8
Task ArithmeticPartitioning=Clustering2026.0427.5
Weight AveragePartitioning=Clustering2026.0427.1
CC12M Split 3Partitioning=Clustering2026.0425.6
CC12M Split 4Partitioning=Clustering2026.0422.5
CC12M Split 2Partitioning=Clustering2026.0422.1
TIES w/ DAREPartitioning=Clustering2026.0419.5
CC12M Split 1Partitioning=Clustering2026.0411.9
Iso-CPartitioning=Clustering2026.048.9