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

Video Perception Reasoning on OVO-Bench Perception

91.95OCR

Qwen3-VL-8B + OASIS

Updated 1mo ago

Evaluation Results

Method	Links
Qwen3-VL-8B + OASIS 2026.04		91.95	80.73	81.03	67.42	67.33	79.89	78.14
Gemini 1.5 Pro 2026.04		85.91	66.97	79.31	58.43	63.37	61.96	69.32
Qwen2.5-VL-7B + OASIS 2026.04		85.23	72.48	66.38	52.25	67.33	64.67	67.26
Qwen3-VL-8B 2026.04		83.89	58.72	70.69	56.18	69.31	64.13	66.79
Qwen2.5-VL-7B 2026.04		76.51	57.8	68.1	46.63	66.34	56.52	60.93
GPT-4o 2026.04		69.8	64.22	71.55	51.12	70.3	59.78	64.46
LLaVA-Video-7B 2026.04		69.13	58.72	68.83	49.44	74.26	59.78	62.32
LLaVA-OneVision-7B 2026.04		66.44	57.8	73.28	53.37	71.29	61.96	62.04
Qwen2-VL-72B 2026.04		65.77	60.55	69.83	51.69	69.31	54.35	61.92
Dispider 2026.04		57.72	49.54	62.07	44.94	61.39	51.63	54.55
StreamChat 2026.04		51.68	47.71	58.62	41.01	61.06	47.83	50.12
Qwen2-VL-7B 2026.04		40.4	50.46	63.76	47.19	66.34	53.55	50.98
Flash-VStream-7B 2026.04		24.16	29.36	28.45	33.71	25.74	28.8	28.37
VideoLLM-online-8B 2026.04		8.05	2.83	12.04	14.04	45.54	21.1	22.22