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

Long-video understanding on Video-MME

88.6Overall Score

Gemini 3 Pro

Updated 1mo ago

Evaluation Results

Method
Gemini 3 Pro 2026.06	88.6	-	-	-	-	-	-	-	-	-
Gemini 2.5 Pro 2026.06	87.8	-	-	-	-	-	-	-	-	-
Gemini-2.5-Pro 2026.03	84.3	-	-	-	-	-	-	-	-	-
Gemini 2.5 Flash 2026.06	84.2	-	-	-	-	-	-	-	-	-
GPT-5 2026.06	83.3	-	-	-	-	-	-	-	-	-
GPT-5 mini 2026.06	77.3	-	-	-	-	-	-	-	-	-
Qwen2.5-VL w/ AdaptToken 2026.03	76.1	-	-	-	-	-	-	-	-	-
Gemini-1.5-Pro 2025.07	75	-	-	-	-	-	-	-	-	-
Gemini-1.5-Pro 2026.06	75	-	-	-	-	-	-	-	-	67.4
Qwen2.5-VL w/ FlexSelect 2026.03	74.4	-	-	-	-	-	-	-	-	-
Claude Sonnet 4.5 2026.06	74.2	-	-	-	-	-	-	-	-	-
Qwen3-VL w/ AdaptToken 2026.03	73.8	-	-	-	-	-	-	-	-	-
InternVideo3 2026.06	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	-	-	-	-	-	-	-	-	-
Keye-VL-1.5-8B 2026.06	73	-	-	-	-	-	-	-	-	-
Eagle2.5-8B 2026.06	72.4	-	-	-	-	-	-	-	-	-
GPT-4o 2026.03	71.9	-	-	-	-	-	-	-	-	-
GPT-4o 2025.07	71.9	-	-	-	-	-	-	-	-	-
GPT-4o 2026.06	71.9	-	-	-	-	-	-	-	-	65.3
Qwen3-VL 2026.03	71.4	-	-	-	-	-	-	-	-	-
Qwen3-VL-8B 2026.06	71.4	-	-	-	-	-	-	-	-	-
Qwen2.5-VL w/ AdaptToken 2026.03	70.5	-	-	-	-	-	-	-	-	-
Gemini-1.5-Flash 2025.07	70.3	-	-	-	-	-	-	-	-	-
Gemini-1.5-Flash 2026.06	70.3	-	-	-	-	-	-	-	-	61.1
Molmo2-8B 2026.06	69.9	-	-	-	-	-	-	-	-	-
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	-	-	-	-	-	-	-	-	-
GLM-4.1V-9B 2026.06	68.2	-	-	-	-	-	-	-	-	-
InternVL2.5 w/ AdaptToken-Lite 2026.03	68.1	-	-	-	-	-	-	-	-	-
MiniCPM-V-4.5-8B 2026.06	67.9	-	-	-	-	-	-	-	-	-
MMProLong 2026.05	67.78	-	-	-	-	-	-	-	-	-
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	-	-	-	-	-	-	-	-	-
VideoLLaMA3 2025.07	66.2	-	-	-	-	-	-	-	-	-
InternVL3.5-8B 2026.06	66	-	-	-	-	-	-	-	-	-
TPO 2026.03	65.6	-	-	-	-	-	-	-	-	-
MiMo-VL w/ Q-Fold 2026.06	65.6	-	-	-	-	-	-	-	-	54.3
Qwen2.5-VL w/ SeViCES 2026.03	65.5	-	-	-	-	-	-	-	-	-
InternVL2.5 w/ Triumph 2026.03	65.4	-	-	-	-	-	-	-	-	-
Qwen2.5-VL 2026.03	65.4	-	-	-	-	-	-	-	-	-
VideoChat-Flash-7B 2026.06	65.3	-	-	-	-	-	-	-	-	-
Qwen2.5-VL 2025.07	65.1	-	-	-	-	-	-	-	-	-
Qwen2.5-VL-7B 2026.05	65.1	-	-	-	-	-	-	-	-	-
InternVideo2.5-7B 2026.06	65.1	-	-	-	-	-	-	-	-	-
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	-	-	-	-	-	-	-	-	-
LLaVA-Video-7B 2026.06	63.3	-	-	-	-	-	-	-	-	-
InternVL3.5-REGATE 2025.07	63	-	-	-	-	-	-	-	-	-
MiMo-VL 2026.06	62.5	-	-	-	-	-	-	-	-	52.6
InternVL3.5 2025.07	62.4	-	-	-	-	-	-	-	-	-
Qwen2.5-VL w/ Q-Fold 2026.06	62.1	-	-	-	-	-	-	-	-	52.6
Qwen2-VL w/ Q-Fold 2026.06	61.7	-	-	-	-	-	-	-	-	51.9
Qwen2.5-VL 2026.06	61.5	-	-	-	-	-	-	-	-	50.8
LLaVA-OneVision-1.5 w/ Q-Fold 2026.06	61.5	-	-	-	-	-	-	-	-	52.2
LongVU 2026.06	60.6	-	-	-	-	-	-	-	-	-
LLaVA-OneVision-1.5 2026.06	60.5	-	-	-	-	-	-	-	-	51.1
LLaVA-NeXT-Video 2025.07	60.2	-	-	-	-	-	-	-	-	-
VILA1.5 2025.07	60.1	-	-	-	-	-	-	-	-	-
LongVILA 2026.06	60.1	-	-	-	-	-	-	-	-	-
GPT-4V 2026.06	59.9	-	-	-	-	-	-	-	-	53.5
Qwen2-VL w/ AKS 2026.06	59.9	-	-	-	-	-	-	-	-	-
Qwen2-VL w/ FOCUS 2026.06	59.7	-	-	-	-	-	-	-	-	-
Qwen2-VL w/ TSPO† 2026.06	59.6	-	-	-	-	-	-	-	-	-
mPLUG-Owl3 2026.03	59.3	-	-	-	-	-	-	-	-	-
mPLUG-Owl3 2026.06	59.3	-	-	-	-	-	-	-	-	50.1
Oryx-1.5 2026.06	58.8	-	-	-	-	-	-	-	-	51.2
Qwen2-VL w/ Q-Frame 2026.06	58.3	-	-	-	-	-	-	-	-	48.3
LLaVA-OneVision 2025.07	58.2	-	-	-	-	-	-	-	-	-
VAMBA 2026.06	57.8	-	-	-	-	-	-	-	-	-
TimeMarker 2026.06	57.3	-	-	-	-	-	-	-	-	46.4
Qwen2-VL 2026.06	57.3	-	-	-	-	-	-	-	-	47.3
Video-XL 2026.06	55.5	-	-	-	-	-	-	-	-	49.2
VideoLLaMA2-REGATE 2025.07	54.5	-	-	-	-	-	-	-	-	-
VideoLLaMA2 2025.07	53.7	-	-	-	-	-	-	-	-	-
LongVA 2026.06	52.6	-	-	-	-	-	-	-	-	46.2
Video-CCAM 2026.06	50.3	-	-	-	-	-	-	-	-	39.6
Video-LLaVA 2025.07	39.9	-	-	-	-	-	-	-	-	-
VideoChat2-REGATE 2025.07	32.7	-	-	-	-	-	-	-	-	-
VideoChat2 2025.07	26	-	-	-	-	-	-	-	-	-
LLaMA-VID 2025.07	25.9	-	-	-	-	-	-	-	-	-
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	-

Showing 100 of 115 rows