TabFact leaderboard

TabFact is an external benchmark published by TabFact: A Large-scale Dataset for Table-based Fact Verification. TabFact asks whether a statement is supported or refuted by a Wikipedia table. It tests decisions that combine language interpretation with structured evidence. Its evaluation set is described by the source as fact verification against tables. The source rates its difficulty as depends on the evaluated split and label mapping.

Each model's result is published by TabFact: A Large-scale Dataset for Table-based Fact Verification as decision classification. ModelScale prints that value exactly as published, and never converts or rescales it. This page ranks the 0 models that carry a published value, highest value first; a model the source never scored is left out rather than ranked at zero. The source does not state whether a higher value is the better result, so neither does this page.