ScoreThe best current run on each benchmark, on the benchmark's metric scaled to 0–100. ± is the 95% sampling margin, from resampling the run's inputs.
RankRank among all current models on that benchmark; ≈ for models that cannot be told apart within sampling error.
Not run on: Bibliographic Data, Blacklist Cards, Book Advert XML Repair, Business Letters, Company Lists, Duty Rosters, Fraktur Adverts, General Meeting Minutes, Library Cards, Medieval Manuscripts, Personnel Cards.
