Video counting on BURST VC (test)
62AccuracyMolmoPoint-Vid-8B
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| MolmoPoint-Vid-8BModel category=MolmoPoint2026.03 | 62 | 76.3 | |
| Molmo2-O-7BModel category=Fully open2026.03 | 61.6 | 76 | |
| MolmoPoint-8BModel category=MolmoPoint2026.03 | 61.6 | 76.9 | |
| Molmo2-4BModel category=Fully open2026.03 | 61.5 | 76.1 | |
| Molmo2-8BModel category=Fully open2026.03 | 60.8 | 75 | |
| GPT-5 miniModel category=API call only2026.03 | 46 | 73 | |
| Gemini 3 ProModel category=API call only2026.03 | 44 | 71.7 | |
| GPT-5Model category=API call only2026.03 | 43.1 | 73.7 | |
| Claude Sonnet 4.5Model category=API call only2026.03 | 42.4 | 72.6 | |
| Qwen3-VL-8BModel category=Open weights2026.03 | 42 | 74.4 | |
| Gemini 2.5 ProModel category=API call only2026.03 | 41.6 | 70 | |
| Qwen3-VL-4BModel category=Open weights2026.03 | 38.9 | 74.7 | |
| Gemini 2.5 FlashModel category=API call only2026.03 | 38.7 | 70 |