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

Video Understanding on VideoRefer-BenchQ

78.3Overall Accuracy

SWIM

Updated 15d ago

Evaluation Results

Method	Links
SWIM 2026.05		78.3	83.8	75	66.7	93.7	80.7
GAR-8B 2025.10		72	77.2	71	61.7	86.6	68.1
VideoRefer-7B 2025.10		71.9	75.4	68.6	59.3	89.4	78.1
VideoRefer-7B 2026.05		71.9	75.4	68.6	59.3	89.4	78.1
Qwen2.5-VL-7B 2026.05		71.8	78	69.7	58.2	79.9	73.2
GPT-4o 2025.10		71.3	62.3	74.5	66	88	73.7
GPT-4o 2026.05		71.3	62.3	74.5	66	88	73.7
GAR-1B 2025.10		69.9	75	69.9	59.7	83.2	63.7
Qwen2.5-Omni-7B 2026.05		68.2	65	67.6	54	84.3	70.3
LLaVA-OneVision-7B 2025.10		67.4	58.7	62.9	64.7	87.4	76.3
LLaVA-OV-7B 2026.05		67.4	58.7	62.9	64.7	87.4	76.3
Qwen2-VL-7B 2025.10		66	62	69.6	54.9	87.3	74.6
Qwen2-VL-7B 2026.05		66	62	69.6	54.9	87.3	74.6
GPT-4o-mini 2026.05		65.8	57.6	67.1	56.5	85.9	75.4
InternVL2-26B 2025.10		65	58.5	63.5	53.4	88	78.9
InternVL2-26B 2026.05		65	58.5	63.5	53.4	88	78.9
LongVA-7B 2026.05		61.8	56.2	62.5	52	83.9	65.8
LongVU-7B 2026.05		61	47.2	61.3	57.5	85.3	65.8
Ferret-7B 2025.10		48.8	35.2	44.7	41.9	70.4	74.6
Ferret-7B 2026.05		48.8	35.2	44.7	41.9	70.4	74.6
Osprey-7B 2025.10		39.9	45.9	47.1	30	48.6	23.7
Osprey-7B 2026.05		39.9	45.9	47.1	30	48.6	23.7