200-way Classification on THINGS-EEG (cross-subject (leave-one-subject-out)) benchmark leaderboard · SOTA2 Research

200-way Classification on THINGS-EEG (cross-subject (leave-one-subject-out))

17.5Sub-01 Top-1 AccuracyMultiview EEG representation learning framework

Evaluation Results

Method
Multiview EEG representation learning framework2026.06	17.5	48.5	15.5	41.5	9	34	12.5	37.5	14.5	42	17	52	14	45	16	47.5	17	49.5	19.5	56	15.3	45.4
UBP2026.06	11.5	29.7	15.5	40	9.8	27	13	32.3	8.8	33.8	11.7	31	10.2	23.8	12.2	32.2	15.5	40.5	16	43.5	12.4	33.4
ATM-S2026.06	10.5	26.8	7.1	24.8	11.9	33.8	14.7	39.4	7	23.9	11.1	35.8	16.1	43.5	15	40.3	4.9	22.7	20.5	46.5	11.8	33.7
NICE2026.06	7.6	22.8	5.9	20.5	6	22.3	6.3	20.7	4.4	18.3	5.6	22.2	5.6	19.7	6.3	22	5.7	17.6	8.4	28.3	6.2	21.4
UMind2026.06	7.5	31	7.5	32	15.5	37.5	17	38.5	8	22.5	10.5	37.5	11.5	30	16	46	10	32.5	16.5	36.5	12	34.4
NICE-SA2026.06	7	22.6	6.6	23.2	7.5	23.7	5.4	21.4	6.4	22.2	7.5	22.5	3.8	19.1	8.5	24.4	7.4	22.3	9.8	29.6	7	23.1
NICE-GA2026.06	5.9	21.4	6.4	22.7	5.5	20.1	6.1	21	4.7	19.5	6.2	22.5	5.9	19.1	7.3	25.3	4.8	18.3	6.2	26.3	5.9	21.6
BraVL2026.06	2.3	8	1.5	6.3	1.4	5.9	1.7	6.7	1.5	5.6	1.8	7.2	2.1	8.1	2.2	7.6	1.6	6.4	2.3	8.5	1.8	7