Item Response Theory Assessment on BX benchmark leaderboard · SOTA2 Research

Item Response Theory Assessment on BX

57.7AUCMMLE

Evaluation Results

Method	Links
MMLE2022.10		57.7	-0.612	—	—
JMLE2022.10		57	-0.62	—	—
Spectral2022.10		54.6	-0.618	—	—
PMLE2022.10		54.6	-0.618	—	0.481
CMLE2022.10		50.3	-0.8	—	0.338