Video Question Answering on LVBench (val)
51ScoreFlexMem
Evaluation Results
| Method | Links | |
|---|---|---|
| FlexMemBase MLLM=LLaVA-Video 7B, Sampled Frames=512/1024frm, Input Tokens=13k2026.03 | 51 | |
| LLaVA-Video + FlexMemLLM=7B2026.03 | 51 | |
| AdaRETAKEBase MLLM=LLaVA-Video 7B, Sampled Frames=1024frm, Input Tokens=40k2026.03 | 49.6 | |
| AKSBase MLLM=LLaVA-Video 7B, Sampled Frames=1fps, Input Tokens=13k2026.03 | 47.4 | |
| FlexMemBase MLLM=LLaVA-OV 7B, Sampled Frames=512/1024frm, Input Tokens=7k2026.03 | 46.2 | |
| Qwen2.5-VLLLM=7B2026.03 | 45.3 | |
| TSPOLLM=7B2026.03 | 45.3 | |
| AKSBase MLLM=LLaVA-OV 7B, Sampled Frames=1fps, Input Tokens=7k2026.03 | 43.5 | |
| mPLUG-Owl3LLM=7B2026.03 | 43.5 | |
| LLaVA-Video 7BBase MLLM=LLaVA-Video 7B, Sampled Frames=64frm, Input Tokens=13k2026.03 | 42.6 | |
| AdaRETAKEBase MLLM=LLaVA-OV 7B, Sampled Frames=1024frm, Input Tokens=20k2026.03 | 42.1 | |
| LLaVA-VideoLLM=7B2026.03 | 42.1 | |
| TimeMarkerLLM=8B2026.03 | 41.3 | |
| LLaVA-OV 7BBase MLLM=LLaVA-OV 7B, Sampled Frames=32frm, Input Tokens=7k2026.03 | 38.4 | |
| Gemini-1.5-ProLLM=-2026.03 | 33.1 | |
| GPT-4oLLM=-2026.03 | 27 |