List your company

Audio-Visual Question Answering on Video-Holmes (Score)

59.9ScoreGemini 2.5 Pro
30.2637.95545.6553.345Oct 14, 2025

Evaluation results

MethodLinks
Gemini 2.5 ProModel Category=Proprietary Models, QA Backbone=GPT-4o, Evaluation Approach=caption-to-QA cascade2025.1059.9
Gemini 2.5 FlashModel Category=Proprietary Models, QA Backbone=GPT-4o, Evaluation Approach=caption-to-QA cascade2025.1052.8
Gemini 2.0 FlashModel Category=Proprietary Models, QA Backbone=GPT-4o, Evaluation Approach=caption-to-QA cascade2025.1051.6
Omni-Captioner-7BModel Category=Open-Source Models, QA Backbone=GPT-4o, Evaluation Approach=caption-to-QA cascade2025.1048.8
video-SALMONN 2-7BModel Category=Open-Source Models, QA Backbone=GPT-4o, Evaluation Approach=caption-to-QA cascade2025.1042.9
Qwen2.5-Omni-7BModel Category=Open-Source Models, QA Backbone=GPT-4o, Evaluation Approach=caption-to-QA cascade2025.1035.7
VideoLLaMA 2-7BModel Category=Open-Source Models, QA Backbone=GPT-4o, Evaluation Approach=caption-to-QA cascade2025.1033.5
video-SALMONN-13BModel Category=Open-Source Models, QA Backbone=GPT-4o, Evaluation Approach=caption-to-QA cascade2025.1031.4