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

Long Video QA on Video-MME

84.3Average Score

Gemini 2.5 Pro

Updated 1mo ago

Evaluation Results

Method	Links
Gemini 2.5 Pro 2025.11		84.3	-	-
VideoChat-M1 2025.11		83.2	84.2	76.7
Qwen3-VL-235B-Instruct 2025.11		79.2	-	-
Qwen3-VL-235B-Thinking 2025.11		79	-	-
Seed 1.5VL 2025.11		77.9	-	-
VideoRAG-72B 2025.11		75.7	72.9	73.1
ReAgent-V-72B 2025.11		75.1	72.3	72.9
Gemini 1.5 Pro 2025.11		75	74.3	67.4
Qwen2.5-VL-72B 2025.11		73.3	-	-
InternVL-3.5-241B 2025.11		72.9	-	-
VideoChat-A1 2025.11		72.9	72.8	65
InternVL-3-78B 2025.11		72.7	-	-
Eagle-2.5-8B 2025.11		72.4	-	-
InternVL-2.5-78B 2025.11		72.1	70.9	62.6
GPT-4o 2025.11		71.9	70.3	65.3
Qwen3-VL-8B-Instruct 2025.11		71.4	-	-
Qwen2-VL-72B 2025.11		71.2	71.3	62.2
InternVL-3.5-78B 2025.11		70.9	-	-
LLAVA-Video-72B 2025.11		70.6	68.9	61.5
Aria-28B 2025.11		67.6	67	58.8
Oryx-34B 2025.11		67.3	65.3	59.3
VideoChat-R1.5-7B 2025.11		67.1	-	-
VideoXL2-8B 2025.11		66.6	-	-
LLaVA-ov-72B 2025.11		66.3	62.2	60
InternVL-3-8B 2025.11		66.3	-	-
InternVL-3.5-8B 2025.11		66	-	-
VideoChat-Flash-7B 2025.11		65.3	-	55.4
InternVideo2.5-7B 2025.11		65.1	-	-
Qwen2.5-VL-7B 2025.11		65.1	-	-
LongRL-7B 2025.11		65.1	63.2	55.2
InternVL-2.5-8B 2025.11		64.2	-	-
VITAL-7B 2025.11		64.1	-	54
Qwen2-VL-7B 2025.11		63.3	-	-
LLaVA-Video-7B 2025.11		63.3	-	-
VideoLLaMA2-72B 2025.11		62.4	59.9	57.6
Video-R1-7B 2025.11		61.4	-	-
LongVILA-7B 2025.11		60.1	58.3	53
LongVA-7B 2025.11		52.6	50.4	46.2
DrVideo 2025.11		51.7	-	-
ShareGPT4Video-8B 2025.11		39.9	36.3	35
VideoChat2-7B 2025.11		39.5	37	33.2
DeepVideoDiscovery 2025.11		-	-	67.3