Video Question Answering on TimeScope (test)
86.2ScoreAdaRETAKE
Evaluation Results
| Method | Links | |
|---|---|---|
| AdaRETAKEBase MLLM=LLaVA-Video 7B, Sampled Frames=1024frm, Input Tokens=40k2026.03 | 86.2 | |
| FlexMemBase MLLM=LLaVA-Video 7B, Sampled Frames=512/1024frm, Input Tokens=13k2026.03 | 85.9 | |
| LLaVA-Video + FlexMemLLM=7B2026.03 | 85.9 | |
| AKSBase MLLM=LLaVA-Video 7B, Sampled Frames=1fps, Input Tokens=13k2026.03 | 85.4 | |
| Qwen2.5-VLLLM=7B2026.03 | 81 | |
| FlexMemBase MLLM=LLaVA-OV 7B, Sampled Frames=512/1024frm, Input Tokens=7k2026.03 | 80.5 | |
| PanelsBase MLLM=LLaVA-Video 7B, Sampled Frames=1fps, Input Tokens=13k2026.03 | 79.2 | |
| AdaRETAKEBase MLLM=LLaVA-OV 7B, Sampled Frames=1024frm, Input Tokens=20k2026.03 | 75.8 | |
| PanelsBase MLLM=LLaVA-OV 7B, Sampled Frames=1fps, Input Tokens=7k2026.03 | 69.5 | |
| LLaVA-Video 7BBase MLLM=LLaVA-Video 7B, Sampled Frames=64frm, Input Tokens=13k2026.03 | 65 | |
| LLaVA-VideoLLM=7B2026.03 | 65 | |
| LLaVA-OV 7BBase MLLM=LLaVA-OV 7B, Sampled Frames=32frm, Input Tokens=7k2026.03 | 56.3 | |
| LongVALLM=7B2026.03 | 55.9 |