Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Natural Language Inference on RTE (Multi-Run Metrics)

81.2Avg Accuracy

T0-11B

45.94455.09764.2573.403Apr 3, 2022May 7, 2022Jun 11, 2022Jul 16, 2022Aug 19, 2022Sep 23, 2022Oct 28, 2022
Updated 4d ago

Evaluation Results

MethodLinks
2022.10
81.2-3.7
2022.10
74-3.8
2022.10
66.8-2.9
2022.04
64.458.53.9
2022.10
64.1-1.4
2022.10
64.1-3.5
2022.04
62.351.34.5
2022.10
62.1-3.1
2022.04
61.353.85.2
2022.04
60.752.74.5
2022.04
60.453.14.7
2022.04
60.149.54.7
2022.04
56.950.74.1
2022.04
56.850.23.5
2022.10
54.1-1.1
2022.10
51.1-3.2
2022.10
50.5-3.2
2022.10
48.4-1.7
2022.10
48.4-2.7
2022.10
47.3-1.7
2022.10
47.3-2.4