List your company

Audio-Visual Question Answering on Daily-Omni

73.6ScoreGemini 2.5 Pro
38.55247.65156.7565.849Oct 14, 2025

Evaluation results

MethodLinks
Gemini 2.5 ProModel Category=Proprietary Models, QA Backbone=GPT-4o, Evaluation Approach=caption-to-QA cascade2025.1073.6
Omni-Captioner-7BModel Category=Open-Source Models, QA Backbone=GPT-4o, Evaluation Approach=caption-to-QA cascade2025.1067.9
Gemini 2.0 FlashModel Category=Proprietary Models, QA Backbone=GPT-4o, Evaluation Approach=caption-to-QA cascade2025.1060.6
video-SALMONN 2-7BModel Category=Open-Source Models, QA Backbone=GPT-4o, Evaluation Approach=caption-to-QA cascade2025.1059.7
Gemini 2.5 FlashModel Category=Proprietary Models, QA Backbone=GPT-4o, Evaluation Approach=caption-to-QA cascade2025.1059.5
Qwen2.5-Omni-7BModel Category=Open-Source Models, QA Backbone=GPT-4o, Evaluation Approach=caption-to-QA cascade2025.1047.9
video-SALMONN-13BModel Category=Open-Source Models, QA Backbone=GPT-4o, Evaluation Approach=caption-to-QA cascade2025.1045
VideoLLaMA 2-7BModel Category=Open-Source Models, QA Backbone=GPT-4o, Evaluation Approach=caption-to-QA cascade2025.1039.9