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

General Reasoning on AGIEval (en)

2.132Speedup Ratio

MTP-D ensemble

1.01921.30811.5971.8859Mar 25, 2026
Updated 23d ago

Evaluation Results

MethodLinks
2026.03
2.132
2026.03
2.071
2026.03
2.068
2026.03
1.964
2026.03
1.94
2026.03
1.87
2026.03
1.851
2026.03
1.766
2026.03
1.764
2026.03
1.735
2026.03
1.535
2026.03
1.51
2026.03
1.337
2026.03
1.128
2026.03
1.062