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

Video Question Answering on VideoMME (Short, Median, Long, Avg. Metrics)

76Short VQA Accuracy

Full Tokens

Updated 18d ago

Evaluation Results

Method	Links
Full Tokens 2026.07		76	68.33	64.89	69.74
Gemini 3.0 Pro 2026.07		75.11	69.67	60.78	68.52
OmniFocus 2026.07		74.78	68	65.44	69.41
Seed 2.0 Pro 2026.07		74.67	68	57.22	66.63
Full Tokens 2026.07		74.11	65.56	60.11	66.59
OmniZip 2026.07		73.67	66	64.33	68
CuRe 2026.07		73.67	66.33	56.33	65.44
OmniFocus 2026.07		73.22	66.89	64.56	68.22
Qwen3.6-35B-A3B 2026.07		73.11	65.67	44.67	61.15
DyCoke 2026.07		73.01	64.33	65.33	67.99
V-LynX-7B 2026.05		73	61.2	53.8	62.7
OmniZip 2026.07		72.89	66.33	64.67	67.96
Random 2026.07		72.11	65	65.67	67.59
DyCoke 2026.07		72.01	63.33	64.33	66.99
OmniFocus 2026.07		71.89	62.56	60	64.81
Random 2026.07		71.44	65.22	65.33	67.33
OmniFocus 2026.07		71.22	62.89	61	65.04
PAVE-7B 2026.05		71.1	59.4	49.2	59.9
OmniZip 2026.07		70.56	63.67	59.89	64.7
OmniZip 2026.07		70.56	63.22	59.78	64.52
LLaVA-OV-7B 2026.05		70.1	56.6	48.9	58.2
DyCoke 2026.07		70.01	62.1	59.78	64
Random 2026.07		67.89	62.56	59.56	63.33
DyCoke 2026.07		67.89	62.56	59.56	63.33
Random 2026.07		67.67	63.22	59.78	63.56
V-LynX-0.5B 2026.05		63.1	50.7	44.6	52.8
Qwen3-VL-235B-A22B-Instruct 2026.07		61.33	53.56	46.56	53.81
Qwen3-VL-30B-A3B-Instruct 2026.07		61	51.33	43.78	52.04
PAVE-0.5B 2026.05		57.8	42.7	37.4	46
OwlCap-7B 2026.07		53.78	41.56	38.33	44.56
LLaVA-OV-0.5B 2026.05		53.4	41.2	37.3	44
Tarsier2-7B 2026.07		40.44	30.78	28.33	33.19