List your company

Short Video Question Answering on Perception Test (val)

74.3AccuracyLLaVA-Video-72B
53.08458.59264.169.608Jan 14, 2025

Evaluation results

MethodLinks
LLaVA-Video-72BModel Group=Open-source (>10B), Parameters=72B, Training set observed=true2025.0174.3
Tarsier2-7BParameters=7B, Training set observed=true2025.0171.6
Previous SOTACitation=[72], Training set observed=true2025.0170
LLaVA-Video-7BModel Group=Open-source (<=10B), Parameters=7B, Training set observed=true2025.0167.9
LLaVA-OV-72BModel Group=Open-source (>10B), Parameters=72B2025.0166.9
Qwen2-VL-72BModel Group=Open-source (>10B), Parameters=72B2025.0166.5
Tarsier-34BModel Group=Open-source (>10B), Parameters=34B2025.0160.4
LLaVA-OV-7BModel Group=Open-source (<=10B), Parameters=7B2025.0157.1
Tarsier-7BModel Group=Open-source (<=10B), Parameters=7B2025.0153.9