Video Understanding on QV Highlights
35.8AccuracyCapRL-Video-178K
Evaluation Results
| Method | Links | |
|---|---|---|
| CapRL-Video-178KBackbone=Molmo2-8B2026.06 | 35.8 | |
| ShareGPT4Video-8B-Video-178KBackbone=Molmo2-8B2026.06 | 25.3 | |
| Tarsier2-7B-Video-178KBackbone=Molmo2-8B2026.06 | 25 | |
| CapRL-Video-178KBackbone=Molmo2-4B2026.06 | 23.1 | |
| GPT-4o-Video-178KBackbone=Molmo2-8B2026.06 | 21.3 | |
| ShareGPT4Video-8B-Video-178KBackbone=Molmo2-4B2026.06 | 13.3 | |
| GPT-4o-Video-178KBackbone=Molmo2-4B2026.06 | 12.4 | |
| Tarsier2-7B-Video-178KBackbone=Molmo2-4B2026.06 | 11.2 |