Share your thoughts, 1 month free Claude Pro on usSee more

Streaming Video Reasoning on StreamingBench Real-Time

89.47Object Perception (OP)

Human

Updated 1mo ago

Evaluation Results

Method	Links
Human 2026.03		89.47	92	93.6	91.47	95.65	92.52	88	88.75	89.74	91.3	91.46
ThinkStream-3B 2026.03		83.74	70.31	76.03	82.69	76.73	78.19	76.85	70.73	74.43	45.21	75
Gemini 1.5 pro 2026.03		79.02	80.47	83.54	79.67	80	84.74	77.78	64.23	71.95	48.7	75.69
LLaVA-NeXT-Video-32B 2026.03		78.2	70.31	73.82	76.8	63.35	69.78	57.41	56.1	64.31	38.86	66.96
Qwen2.5-VL-7B 2026.03		77.93	76.56	78.55	80.86	76.73	76.95	80.56	65.45	65.72	52.85	73.31
GPT-4o 2026.03		77.11	80.47	83.91	76.47	70.19	83.8	66.67	62.19	69.12	49.22	73.28
Qwen2.5-VL-32B 2026.03		76.29	79.69	78.55	83.5	76.1	79.44	80.56	61.38	68.27	59.07	74.27
Dispider-7B 2026.03		74.92	75.53	74.1	73.08	74.44	59.92	76.14	62.91	62.16	45.8	67.63
Claude 3.5 Sonnet 2026.03		73.33	80.47	84.09	82.02	75.39	79.53	61.11	61.79	69.32	43.09	72.44
LongVA-7B 2026.03		70.03	63.28	61.2	70.92	62.73	59.5	61.11	53.66	54.67	34.72	59.96
Qwen2.5-VL-3B 2026.03		67.21	68.75	75.39	79.17	72.96	72.27	71.3	61.38	71.59	26.06	67.96
VILA-1.5-8B 2026.03		53.68	49.22	70.98	56.86	53.42	53.89	54.63	48.78	50.14	17.62	52.32
VideoLLM-online-8B 2026.03		39.07	40.06	34.49	31.05	45.96	32.4	31.48	34.16	42.49	27.89	35.99
Flash-VStream-7B 2026.03		25.89	43.57	24.91	23.87	27.33	13.08	18.52	25.2	23.87	48.7	23.23