Zero-shot Commonsense Reasoning Suite (PIQA, SIQA, HellaSwag, ARC-E, ARC-C, WinoGrande, LAMBADA) benchmark leaderboard · SOTA2 Research

Zero-shot Commonsense Reasoning Suite (PIQA, SIQA, HellaSwag, ARC-E, ARC-C, WinoGrande, LAMBADA)

66.92PIQA AccuracyReMoE

Evaluation Results

Method	Links
ReMoE2026.05		66.92	38.79	32.66	55.93	24.57	51.41	27.1	42.48
Dense2026.05		66.87	37.77	32.92	56.27	24.74	51.7	29.34	42.8
DeepSeek-V32026.05		66.32	38.38	32.71	55.18	24.91	51.07	28.06	42.38
DECO2026.05		66.14	38.74	32.69	56.41	23.72	51.78	26.57	42.29
BlockFFN2026.05		66.1	38.59	32.51	56.36	24.15	51.38	27.3	42.34
ReMoE2026.05		66.05	38.69	32.08	55.26	24.32	52.33	27.19	42.27
DeepSeek-V32026.05		65.94	37.87	32.75	54.67	23.38	52.49	27.03	42.02
DECO2026.05		65.94	39.61	32.78	57.11	25.43	53.28	25.5	42.81
TopP2026.05		64.53	36.44	31.42	50.55	22.53	51.07	14.13	38.67
DECO2026.05		60.94	36.85	27.96	45.84	20.22	50.67	15.8	36.9
BlockFFN2026.05		60.83	36.28	27.62	44.87	19.45	50.12	16.55	36.53
Dense2026.05		60.77	35.57	28.03	45.88	20.22	50.59	16.51	36.8
DeepSeek-V32026.05		60.66	36.63	27.76	45.76	20.05	50.43	15.85	36.73
ReMoE2026.05		60.34	36.59	27.72	46.34	18.43	51.22	15.6	36.61
TopP2026.05		60.17	35.21	27.67	42.38	18.86	50.91	7.74	34.71
DeepSeek-V32026.05		60.12	35.93	27.85	44.15	19.45	50.75	15.89	36.31
ReMoE2026.05		59.74	35.16	27.96	46.09	19.54	49.96	17.76	36.6
DECO2026.05		58.22	35.93	27.65	42.51	19.03	51.3	15.84	35.78