TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/VideoLLaMA2 (72B)

VideoLLaMA2 (72B)

Reported on 8 benchmarks across 2 tasks · 1 paper · 2 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Reasoning5 results

  • Video Question AnsweringonEgoSchema (fullset)
    Accuracy· 2024-06-11
    63.9
    best: 71.14 (BIMBA-LLaVA-Qwen2-7B)
    SOTA
    VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMsarXiv:2406.07476
  • Video Question AnsweringonPerception Test
    Accuracy (Top-1)· 2024-06-11
    57.5
    best: 71.4 (Oyrx (34B))
    VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMsarXiv:2406.07476
  • Video Question AnsweringonMVBench
    Avg.· 2024-06-11
    62
    best: 69.3 (LinVT-Qwen2-VL (7B))
    VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMsarXiv:2406.07476
  • Video Question AnsweringonVideo-MME (w/o subs)
    Accuracy (%)· 2024-06-11
    60.9
    best: 77.4 (Video-RAG (based on LLaVA-Video))
    VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMsarXiv:2406.07476
  • Video Question AnsweringonVideo-MME
    Accuracy (%)· 2024-06-11
    63.1
    best: 81.3 (Gemini 1.5 Pro)
    VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMsarXiv:2406.07476

Natural Language Processing3 results

  • Question AnsweringonEgoSchema (fullset)
    Accuracy· 2024-06-11
    63.9
    best: 71.14 (BIMBA-LLaVA-Qwen2-7B)
    SOTA
    VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMsarXiv:2406.07476
  • Question AnsweringonVideo-MME (w/o subs)
    Accuracy (%)· 2024-06-11
    60.9
    best: 77.4 (Video-RAG (based on LLaVA-Video))
    VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMsarXiv:2406.07476
  • Question AnsweringonVideo-MME
    Accuracy (%)· 2024-06-11
    63.1
    best: 81.3 (Gemini 1.5 Pro)
    VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMsarXiv:2406.07476