LLaVA-OneVision (72B)
Reported on 2 benchmarks across 2 tasks
Note: results are matched by exact model name. Different papers may use the same name for different model variants.
Natural Language Processing1 result
- Accuracy (%)64.8best: 77.4 (Video-RAG (based on LLaVA-Video))
Reasoning1 result
- Accuracy (%)64.8best: 77.4 (Video-RAG (based on LLaVA-Video))