Long-context language modeling evaluation on HELMET benchmark leaderboard · SOTA2 Research

Long-context language modeling evaluation on HELMET

0Average SparsityFullAttention

Evaluation Results

Method	Links
FullAttention2026.02		0	50.33	48.87	46.11	43.83	41.07	46.04
FullAttention2026.02		0	67.09	67.42	66.78	65.73	62.8	65.96
FullAttention2026.02		0	61.17	58.67	56.71	55.81	49.74	56.42
FullAttention2026.02		0	54.75	50.66	48.4	44.98	39.59	47.68
FlexPrefill2026.02		37.88	53.18	49.05	46.48	43.01	35.52	45.45
FlexPrefill2026.02		38.63	60.73	58.15	56.22	55.15	49.87	56.02
FlexPrefill2026.02		40.16	50.87	50.01	46	43.87	40.92	46.33
XAttention2026.02		41.96	66.51	67.22	66.38	63.75	61.17	65.01
RRAttention2026.02		43.01	66.96	67.63	66.55	64.46	61.66	65.45
XAttention2026.02		47.35	53.9	49.77	46.96	44.49	38.09	46.64
XAttention2026.02		47.5	60.79	58.1	55.57	54.78	49.45	55.74
RRAttention2026.02		47.56	54.22	50.02	47.92	45.17	38.51	47.17
FlexPrefill2026.02		48.22	66.15	65.61	64.97	63.2	60.8	64.15
RRAttention2026.02		48.68	61.22	58.21	56.07	55.33	50.37	56.24
XAttention2026.02		50.8	50.41	48.51	44.73	43.69	41.17	45.7
RRAttention2026.02		51.86	50.95	49.45	47.13	44.12	41.06	46.54
XAttention2026.02		55.2	66.78	67.19	65.25	63.12	60.04	64.48
RRAttention2026.02		56.26	67.01	66.6	65.71	62.97	60.7	64.6
FlexPrefill2026.02		58.42	64.08	64.11	63.15	61.64	59.3	62.46
XAttention2026.02		59.15	52.53	47.72	45.72	43.35	37.04	45.27
RRAttention2026.02		59.53	53.37	49.31	47.35	44.62	38.48	46.63
XAttention2026.02		59.88	59.92	57.15	55.54	53.66	47.82	54.82
RRAttention2026.02		61.02	60.95	58.43	55.86	54.27	48.85	55.67
FlexPrefill2026.02		63.21	44.11	40.59	40.6	36.39	29.66	38.27
XAttention2026.02		63.85	50.28	47.79	44.17	43.31	40.19	45.15
RRAttention2026.02		64.05	50.79	48.58	46.48	43.89	40.77	46.1
FlexPrefill2026.02		65.98	44.99	44.51	43.27	41.31	38.73	42.56
FlexPrefill2026.02		66.07	56.02	54.48	53.01	50.77	48.42	52.54