Benchmark Radar™
Star —

PragMatch Benchmark

Explore score history ↗

PragMatch is a controlled set of 3,000 image-text pairs derived from MMSD2.0 for studying pragmatic incongruity in multimodal sarcasm detection, with original sarcastic examples and constructed literal and hard-negative pairs.

Released
2026-08-10
Institutions
Saarland University · Max Planck Institute for Informatics
Evaluates
General AI, Multimodal
Openness
unknown
Importer
Claire Radar
Review status
unreviewed

PragMatch paper

No reported scores are on record for this benchmark yet.

Which sources cite PragMatch?

Related General AI, Multimodal benchmarks