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

Long-video understanding on Video-MME

84.3Overall Score

Gemini-2.5-Pro

Updated 18d ago

Evaluation Results

Method
Gemini-2.5-Pro 2026.03	84.3	-	-	-	-	-	-	-	-
Qwen2.5-VL w/ AdaptToken 2026.03	76.1	-	-	-	-	-	-	-	-
Qwen2.5-VL w/ FlexSelect 2026.03	74.4	-	-	-	-	-	-	-	-
Qwen3-VL w/ AdaptToken 2026.03	73.8	-	-	-	-	-	-	-	-
Qwen2.5-VL w/ AdaReTAKE 2026.03	73.5	-	-	-	-	-	-	-	-
Qwen2.5-VL 2026.03	73.4	-	-	-	-	-	-	-	-
Gemini-1.5-Pro 2026.03	73.2	-	-	-	-	-	-	-	-
GPT-4o 2026.03	71.9	-	-	-	-	-	-	-	-
Qwen3-VL 2026.03	71.4	-	-	-	-	-	-	-	-
Qwen2.5-VL w/ AdaptToken 2026.03	70.5	-	-	-	-	-	-	-	-
Qwen2.5-VL w/ AdaptToken-Lite 2026.03	69.8	-	-	-	-	-	-	-	-
InternVL2.5 w/ AdaptToken 2026.03	68.3	-	-	-	-	-	-	-	-
Qwen2.5-VL w/ FlexSelect 2026.03	68.2	-	-	-	-	-	-	-	-
InternVL2.5 w/ AdaptToken-Lite 2026.03	68.1	-	-	-	-	-	-	-	-
Qwen2.5-VL w/ AdaReTAKE 2026.03	67.7	-	-	-	-	-	-	-	-
ViLAMP 2026.03	67.5	-	-	-	-	-	-	-	-
InternVL2.5 w/ FlexSelect 2026.03	67	-	-	-	-	-	-	-	-
Qwen2.5-VL w/ TimeSearch-R 2026.03	66.6	-	-	-	-	-	-	-	-
VideoLLaMA3 2026.03	66.2	-	-	-	-	-	-	-	-
TPO 2026.03	65.6	-	-	-	-	-	-	-	-
Qwen2.5-VL w/ SeViCES 2026.03	65.5	-	-	-	-	-	-	-	-
InternVL2.5 w/ Triumph 2026.03	65.4	-	-	-	-	-	-	-	-
Qwen2.5-VL 2026.03	65.4	-	-	-	-	-	-	-	-
InternVL2.5 w/ SeViCES 2026.03	64.7	-	-	-	-	-	-	-	-
ByteVideoLLM 2026.03	64.6	-	-	-	-	-	-	-	-
InternVL2.5 w/ ZoomV 2026.03	64.4	-	-	-	-	-	-	-	-
NVILA 2026.03	64.2	-	-	-	-	-	-	-	-
InternVL2.5 2026.03	64.2	-	-	-	-	-	-	-	-
Qwen2.5-VL w/ ZoomV 2026.03	63.6	-	-	-	-	-	-	-	-
mPLUG-Owl3 2026.03	59.3	-	-	-	-	-	-	-	-
Gemini 1.5 Pro 2026.03	-	81.7	84.5	74.3	81	67.4	77.4	75	81.3
GPT-4o 2026.03	-	80	82.8	70.3	76.6	65.3	72.1	71.9	77.2
Gemini 1.5 Flash 2026.03	-	78.8	79.8	68.8	74.7	61.1	68.8	70.3	75
GPT-4V 2026.03	-	70.5	73.2	55.8	59.7	53.5	56.9	59.9	63.3
Qwen2-VL-72B 2026.03	-	80.1	82.2	71.3	76.8	62.2	74.3	71.2	77.8
LLaVA-Video-72B 2026.03	-	81.4	82.8	68.9	75.6	61.5	72.5	70.6	76.9
Qwen3-VL-8B 2026.03	-	76.4	79.2	62.3	72.6	55.9	70.8	64.9	74.2
VideoLLaMA 3-7B 2026.03	-	80.1	80.2	63.7	69.6	54.9	61	66.2	70.3
VideoLLaMA 2-72B 2026.03	-	69.8	72	59.9	63	57.6	59	62.4	64.7
VITA 1.5-7B 2026.03	-	67	69.9	54.2	55.7	47.1	50.4	56.1	58.7
Long-LLaVA-7B 2026.03	-	61.9	66.2	51.4	54.7	45.4	50.3	52.9	57.1
LongVA-7B 2026.03	-	61.1	61.6	50.4	53.6	46.2	47.6	52.6	54.3
Video-LLaVA-7B 2026.03	-	45.3	46.1	38	40.7	36.2	38.1	39.9	41.6
Vgent 2026.03	-	-	-	-	-	-	-	68.9	74.3
VideoRAG 2026.03	-	-	67.1	-	60.4	-	60.1	60.5	62.6
VideoMiner 2026.03	-	65.6	-	57.5	-	52.2	-	58.4	-
VideoTree 2026.03	-	55.5	-	49.2	-	39.3	-	48	-
MM-Mem 2026.03	-	81.5	82.8	69.6	75.8	66.1	75.7	72.4	78.1