Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Natural Language Inference on MultiNLI

82.4Accuracy

ERM

68.46472.08275.779.318Nov 1, 2024Jan 1, 2025Mar 4, 2025May 5, 2025Jul 5, 2025Sep 5, 2025Nov 6, 2025
Updated 1mo ago

Evaluation Results

MethodLinks
2024.11
82.467.9
2025.11
81.768.5
2025.11
81.468.5
2025.11
81.176
2025.11
8168.8
2025.11
80.966.8
2025.11
80.969.1
2025.11
80.966.9
80.769.5
2025.11
80.769.4
2025.11
80.769.6
2025.11
80.672.2
2025.11
80.476.8
2025.11
80.373.3
2024.11
8070.2
2024.11
79.873.6
2025.11
78.869.1
2025.11
77.863.6
2025.11
77.272.3
2025.11
75.163
2025.11
71.763.6
2025.11
69.165.8
2025.11
6966.8