General Video Understanding on TOMATO
37.7AccuracyGPT-4o
Evaluation Results
| Method | Links | |
|---|---|---|
| GPT-4o2025.12 | 37.7 | |
| DNA-Train-7B2025.12 | 32.6 | |
| Tarsier2-7B-Video-178KBackbone=Molmo2-8B2026.06 | 31.4 | |
| Tarsier2-7B-Video-178KBackbone=Molmo2-4B2026.06 | 30.7 | |
| CapRL-Video-178KBackbone=Molmo2-4B2026.06 | 30.7 | |
| CapRL-Video-178KBackbone=Molmo2-8B2026.06 | 30.3 | |
| ShareGPT4Video-8B-Video-178KBackbone=Molmo2-8B2026.06 | 29.5 | |
| GPT-4o-Video-178KBackbone=Molmo2-8B2026.06 | 29.1 | |
| ShareGPT4Video-8B-Video-178KBackbone=Molmo2-4B2026.06 | 28 | |
| GPT-4o-Video-178KBackbone=Molmo2-4B2026.06 | 27.1 | |
| Qwen2.5-VL-7B2025.12 | 26.8 | |
| Video-LLaVA-7B2025.12 | 23.6 | |
| LLaVA-Next-Video2025.12 | 20.1 |