Video Counting on BURST-VideoCount (test)
61.6AccuracyMolmo2-O-7B
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| Molmo2-O-7BModel Category=Molmo2 family: Open weights, Open data (no distillation), Open code, Frames=384, Decoding=greedy2026.01 | 61.6 | 76 | |
| Molmo2-4BModel Category=Molmo2 family: Open weights, Open data (no distillation), Open code, Frames=384, Decoding=greedy2026.01 | 61.5 | 76.1 | |
| Molmo2-8BModel Category=Molmo2 family: Open weights, Open data (no distillation), Open code, Frames=384, Decoding=greedy2026.01 | 60.8 | 75 | |
| GPT-5 miniModel Category=API call only, Frames=384, Decoding=greedy2026.01 | 46 | 73 | |
| Gemini 3 ProModel Category=API call only, Frames=384, Decoding=greedy2026.01 | 44 | 71.7 | |
| GPT-5Model Category=API call only, Frames=384, Decoding=greedy2026.01 | 43.1 | 73.7 | |
| Claude Sonnet 4.5Model Category=API call only, Frames=384, Decoding=greedy2026.01 | 42.4 | 72.6 | |
| Qwen3-VL-8BModel Category=Open weights only, Frames=384, Decoding=greedy2026.01 | 42 | 74.4 | |
| Gemini 2.5 ProModel Category=API call only, Frames=384, Decoding=greedy2026.01 | 41.6 | 70 | |
| Qwen3-VL-4BModel Category=Open weights only, Frames=384, Decoding=greedy2026.01 | 38.9 | 74.7 | |
| Gemini 2.5 FlashModel Category=API call only, Frames=384, Decoding=greedy2026.01 | 38.7 | 70 |