Benchmark Almanac

Cornell University

We track 6 benchmarks that Cornell University made or helped make.

0 in use 4 with public code 2 with a leaderboard here

Benchmarks

Name Kind Released Best score Status
C3 Models answer 19,577 multiple-choice questions on Chinese dialogues and texts from Chinese-as-a-second-language exams. Scoring is accuracy. Reading in many languages Apr 2019 97.8% Dropped
PianoBench Models answer questions about piano performances from recordings or symbolic transcriptions. The authors compare accuracy with and without access to the music. Audio understanding and voice Nov 2026 93.2% Not in cards
KiloGram Models choose which of ten tangram pictures matches a description. The descriptions can name the whole shape or explain what its pieces represent. Spatial reasoning and counting Nov 2022 Not in cards
Med-EASi Models rewrite English medical passages in plain language. The references mark replacements, explanations, insertions, and deletions. Medicine Feb 2023 Not in cards
Natural World Tasks (NeWT 2021) Models distinguish pairs of labels in wildlife photographs. The 164 tasks include recognizing life stages, animal behavior and scene context. General visual questions Mar 2021 Not in cards
OHSUMED Systems rank medical articles for 106 questions from physicians. The original study measured precision and recall against physicians' judgments of which articles were relevant. Medicine Jul 1994 Not in cards