Model

ERNIE 2.0 Base

Baidu

yiyan.baidu.com

Knowledge & Reasoning

Knowledge & Reasoning
BenchmarkScoreMetricHarnessSourceConfidenceLink
DuReader61.3exact_matchN/AIndependentmediumarxiv.org
MRPC86.1accuracyN/AIndependentmediumarxiv.org
MultiNLI86.1matchedN/AIndependentmediumarxiv.org
QNLI92.9accuracyN/AIndependentmediumarxiv.org
Quora Question Pairs89.8accuracyN/AIndependentmediumarxiv.org
RTE74.8accuracyN/AIndependentmediumarxiv.org

Multimodal

Multimodal
BenchmarkScoreMetricHarnessSourceConfidenceLink
CoLA55.2accuracyN/AIndependentmediumarxiv.org

Reproduced by the community

Loading community runs…