evaluation-task · Source-linked discovery

DROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphs

Evaluates reading comprehension where models must resolve references in a question, perhaps to multiple input positions, and perform discrete operations over them (such as addition, counting, or sorting).

Open interactive record →
OriginDheeru Dua, Yizhong Wang, Pradeep Dasigi et al.TopicsGeneral capabilityStatusimported

Can support

Not independently assessed by FronteraEval yet.

Cannot support by itself

No inference beyond the upstream source should be made until the protocol is reviewed.

Original sources