LongVU (7B)
Reported on 5 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.
Reasoning3 results
- Accuracy· 2024-10-22SOTA67.6best: 71.14 (BIMBA-LLaVA-Qwen2-7B)
- Avg.· 2024-10-2266.9best: 69.3 (LinVT-Qwen2-VL (7B))
- Accuracy (%)· 2024-10-2260.6best: 81.3 (Gemini 1.5 Pro)
Natural Language Processing2 results
- Accuracy· 2024-10-22SOTA67.6best: 71.14 (BIMBA-LLaVA-Qwen2-7B)
- Accuracy (%)· 2024-10-2260.6best: 81.3 (Gemini 1.5 Pro)