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

Multiple Choice Classification on OpenBookQA, ARC-Easy, WinoGrande, HellaSwag, PIQA, and MathQA

35Accuracy (OpenBookQA)

Original

19.423.4527.531.55Nov 14, 2024
Updated 8d ago

Evaluation Results

MethodLinks
2024.11
35807360804061
2024.11
34757057792757
2024.11
33797058773659
2024.11
33797259783860
2024.11
32727052752454
2024.11
32727056782656
2024.11
31716849712252
2024.11
29536441681745
2024.11
29776451723054
2024.11
28666646712550
2024.11
20596141693047