Model

ERNIE 2.0 Large

Baidu

yiyan.baidu.com

Knowledge & Reasoning

Knowledge & Reasoning
BenchmarkScoreMetricHarnessSourceConfidenceLink
DuReader64.2exact_matchN/AIndependentmediumarxiv.org
MRPC87.4accuracyN/AIndependentmediumarxiv.org
MultiNLI88.7matchedN/AIndependentmediumarxiv.org
QNLI94.6accuracyN/AIndependentmediumarxiv.org
Quora Question Pairs90.1accuracyN/AIndependentmediumarxiv.org
RTE80.2accuracyN/AIndependentmediumarxiv.org
WNLI67.8accuracyN/AIndependentmediumarxiv.org

Multimodal

Multimodal
BenchmarkScoreMetricHarnessSourceConfidenceLink
CoLA63.5accuracyN/AIndependentmediumarxiv.org

Reproduced by the community

Loading community runs…