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

Question Answering on ScienceQA, CommonsenseQA, and OpenbookQA

93.12ScienceQA Accuracy

Full-Parameter

51.592862.373973.15583.9361Mar 12, 2026
Updated 2mo ago

Evaluation Results

MethodLinks
2026.03
93.1277.4880.483.67
2026.03
91.9177.8982.884.2
2026.03
91.3979.0380.483.6
2026.03
91.0175.517781.17
2026.03
90.7476.4176.681.25
2026.03
90.027678.481.47
2026.03
53.1947.8245.848.94