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

Theory of Mind reasoning on OpenToM narrative

100Location Accuracy (Cg, First)

SFT

46.9660.7374.588.27Jun 8, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.06
10081925688764993.337177.43-
2026.06
9988946791855794.6780835.57
2026.06
998596689079659577.3383.14-
2026.06
989197859087769587.6789.146
2026.06
9784937188823692.677978.714.43
2026.06
8150816356553572.675660.1417.29
2026.06
576460486660436157.3356.8626.28
2026.06
515028155348394437.6740.5736.86
2026.06
5053444470404754.6745.6749.7133.43
2026.06
4951483355533650.6745.6746.4336.71