Our new X account is live! Follow @wizwand_team for updates

Reactive Question Answering on StreamingBench excluding PO 1.0 (test)

76.96Overall Performance (OP)

ROMA

Updated 4d ago

Evaluation Results

Method	Links
ROMA 2026.01		76.96	78.91	77.92	82.05	74.84	72.9	82.41	61.79	65.91	51.06	40.4	34.8	50.4	58.8	37.6	34	44.47
ROMA 2026.01		76.69	82.03	78.86	82.05	74.84	72.9	79.63	59.76	64.49	50.53	38.8	29.6	46.4	51.6	33.2	27.6	22.8
ROMA 2026.01		76.13	70.49	74.14	82.4	72.86	70.8	84.78	63.2	64.91	51.69	39.75	30.36	45.87	47.2	35.27	24.79	24.8
ROMA 2026.01		75.61	81.25	76.97	82.37	71.7	75.08	81.48	62.2	65.62	50	39.6	30.8	59.38	52.4	35.6	28	26.4
ROMA 2026.01		75.61	80.47	79.18	82.37	73.58	75.08	82.41	63.1	65.34	47.34	39.6	28.8	44.4	51.6	35.6	28.4	26.4
ROMA 2026.01		75.51	85.71	76.19	78.23	59.77	61.05	73.21	60	59.67	23.38	38.8	26	40.8	47.2	35.6	27.2	26.8
Dispider 2026.01		74.92	75.53	74.1	73.08	74.44	59.52	76.14	62.91	62.16	45.8	35.46	25.26	38.57	43.34	39.62	27.65	33.61
VideoLLM-Online 2026.01		39.07	40.06	34.49	31.05	45.96	32.4	31.48	34.16	42.49	27.89	31.2	26.51	24.1	32	24.19	29.2	26.55
Flash-VStream 2026.01		25.89	43.57	24.91	23.87	27.33	13.08	18.52	25.2	23.87	48.7	25.91	24.9	25.6	28.4	24.8	25.2	24.12