Large Language Model Downstream Evaluation on General Downstream Suite benchmark leaderboard · SOTA2 Research

Large Language Model Downstream Evaluation on General Downstream Suite

55.51MMLUNITP

Evaluation Results

Method	Links
NITP2026.05		55.51	32.29	50.87	59.97	69.38	43.48	70.1	59.95	75.2	78.36	38.69	52.62	15.83	54.02
NTP2026.05		55.09	31.71	47.67	57.65	69.03	42.89	67.7	59.46	75.2	75.51	35.08	50.27	13.39	52.36