Classification on C3, CMNLI, CHID, BoolQ, WSC, HeSW, PIQA, CoQA, Race-M, Race-H, MMLU, and CMMLU Suite

62.41C3Dense

Evaluation results

Method
Dense2026.02	62.41	33.28	9.59	62.94	66.65	64.33	74.59	66	50.77	52.2	54.68	56.91	53.2
Dense2026.02	62.41	33.28	9.59	62.94	66.65	64.33	74.59	66	50.77	52.2	54.68	56.91	53.2
Dense2026.02	54.08	32.98	36.99	69.79	71.1	74.66	80.96	71.42	70.61	63.15	66.74	50.87	59.07
GradMAP2026.02	49.7	33.64	12.89	41.96	62.5	51.16	66.21	23.12	24.47	27.54	30.17	51.84	39.6
GradMAP2026.02	49.7	33.64	12.89	41.96	62.5	51.16	66.21	23.12	24.47	27.54	30.17	51.84	39.6
GradMAP2026.02	47.67	33.43	26.97	53.79	62.5	60.05	72.91	58.72	40.74	33.85	55.63	40.77	48.92
ShortGPT2026.02	47.45	33.53	5.49	54.71	65.38	46.56	62.68	23.26	24.5	27	28.59	40.62	38.31
ShortGPT2026.02	47.45	33.53	5.49	54.71	65.38	46.56	62.68	23.26	24.5	27	28.59	40.62	38.31
GradMAP2026.02	47.07	32.72	26.07	53.15	63.5	58.54	73.45	59.13	40.6	35.48	54.98	39.6	48.68
GradMAP2026.02	46.58	33.37	10.94	43.88	63.46	50.53	66.49	22.91	23.84	28.92	30.77	48.89	39.21
GradMAP2026.02	46.58	33.37	10.94	43.88	63.46	50.53	66.49	22.91	23.84	28.92	30.77	48.89	39.21
ShortGPT2026.02	43.23	33.13	7.09	57.86	63.5	55.71	69.21	54.22	35.17	35.17	56.69	35.12	45.5
SLEB2026.02	39.18	31.7	11.59	38.29	60.58	30.59	57.73	22.28	21.31	25.27	25.42	22.36	32.2
SLEB2026.02	39.18	31.7	11.59	38.29	60.58	30.59	57.73	22.28	21.38	25.27	25.42	22.36	32.2
Dense2026.02	37.86	32.83	13.14	64.04	66.35	62.77	75.73	56.92	25.63	25.81	24.82	25.33	41.04
SLEB2026.02	37.15	33.1	11.79	54.43	62.5	48.96	70.46	39.72	21.31	21.38	25.29	25.29	37.62
GradMAP2026.02	36.16	32.97	7.09	60.61	65.38	49.78	68.39	38.33	25.49	23.38	24.74	24.87	38.1
GradMAP2026.02	36.11	32.96	2.9	59.76	64.42	49.36	68.01	38.82	25.63	24.24	24.67	25.03	37.66
SLEB2026.02	35.56	32.8	0	45.63	63.46	50.88	72.25	42.18	22.77	23.79	24.4	25.25	36.58
ShortGPT2026.02	25.97	32.89	0.05	45.14	56.73	26.33	53.1	17.61	22.28	22.16	23.63	25.24	29.26