Video Understanding on PerceptionTest (val)
82.3AccuracyMolmoPoint-8B
Evaluation Results
| Method | Links | |
|---|---|---|
| MolmoPoint-8BCategory=MolmoPoint2026.03 | 82.3 | |
| InternVL2.5-2BTotal Params=2.2B, Input Res.=448×448, Num Frames=32, Throughput=21.82025.03 | 66.3 | |
| Mobile-VideoGPT-1.5BTotal Params=1.6B, Input Res.=224×224, Num Frames=16, Throughput=41.02025.03 | 65.3 | |
| AVS + SVC2026.02 | 60.4 | |
| Mobile-VideoGPT-0.5BTotal Params=0.6B, Input Res.=224×224, Num Frames=16, Throughput=45.92025.03 | 58.7 | |
| LongVILALLM Size=7B2024.08 | 58.1 | |
| VideoLLaMA2.1LLM Size=7B2024.08 | 57.3 | |
| LLAVA-OVLLM Size=7B2024.08 | 57.1 | |
| LLaVA-OneVision-7BParameter Scale=7B2026.02 | 57.1 | |
| VideoLLaMA2LLM Size=7B2024.08 | 54.6 | |
| LLaVA-OneVision-0.5BTotal Params=1.0B, Input Res.=384×384, Num Frames=32, Throughput=22.72025.03 | 49.2 | |
| VideoChat2-7BTotal Params=7.3B, Input Res.=224×224, Num Frames=16, Throughput=11.42025.03 | 47.3 |