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

Commonsense Question Answering on CommonSenseQA n=1700 (20%)

68.12Accuracy

MTO-MCP

49.431254.283159.13563.9869Jun 23, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.06
68.12
2026.06
67.12
2026.06
66.25
2026.06
65.83
2026.06
65.16
2026.06
65.15
2026.06
63.09
2026.06
59.57
2026.06
59.21
2026.06
59.02
2026.06
58.47
2026.06
50.23
2026.06
50.15