VideoLLaMA 2 is a set of Video Large Language Models (Video-LLMs) designed to enhance spatial-temporal modeling and audio understanding in video and audio-oriented tasks. Building on its predecessor, VideoLLaMA 2 incorporates a custom Spatial-Temporal Convolution (STC) connector to effectively capture the intricate spatial and temporal dynamics of video data. Additionally, an Audio Branch is integrated through joint training, enriching the model's multi-modal understanding capabilities by seamlessly incorporating audio cues. Comprehensive evaluations on multiple-choice video question answering (MC-VQA), open-ended video question answering (OE-VQA), and video captioning (VC) tasks demonstrate that VideoLLaMA 2 consistently achieves competitive results among open-source models and even approaches some proprietary models on several benchmarks. The model also shows reasonable improvements in audio-only and audio-video question-answering (AQA & OE-AVQA) benchmarks over existing models, highlighting its superior performance in multimodal comprehension. All models are publicly available to facilitate further research.VideoLLaMA 2 is a set of Video Large Language Models (Video-LLMs) designed to enhance spatial-temporal modeling and audio understanding in video and audio-oriented tasks. Building on its predecessor, VideoLLaMA 2 incorporates a custom Spatial-Temporal Convolution (STC) connector to effectively capture the intricate spatial and temporal dynamics of video data. Additionally, an Audio Branch is integrated through joint training, enriching the model's multi-modal understanding capabilities by seamlessly incorporating audio cues. Comprehensive evaluations on multiple-choice video question answering (MC-VQA), open-ended video question answering (OE-VQA), and video captioning (VC) tasks demonstrate that VideoLLaMA 2 consistently achieves competitive results among open-source models and even approaches some proprietary models on several benchmarks. The model also shows reasonable improvements in audio-only and audio-video question-answering (AQA & OE-AVQA) benchmarks over existing models, highlighting its superior performance in multimodal comprehension. All models are publicly available to facilitate further research.