Video Question Answering on Molmo QA Benchmarks Short Video 19 (Avg.)
73.1Short Video Avg.GPT-5
Evaluation Results
| Method | Links | |
|---|---|---|
| GPT-5Access=API call only2026.03 | 73.1 | |
| Gemini 2.5 ProAccess=API call only2026.03 | 71.1 | |
| Gemini 3 ProAccess=API call only2026.03 | 71 | |
| Molmo2-8BAccess=Fully open2026.03 | 69.9 | |
| MolmoPoint-8BAccess=MolmoPoint2026.03 | 69.5 | |
| Molmo2-4BAccess=Fully open2026.03 | 69.3 | |
| PLM-8BAccess=Fully open2026.03 | 68.5 | |
| Molmo2-O-7BAccess=Fully open2026.03 | 68.1 | |
| Gemini 2.5 FlashAccess=API call only2026.03 | 67 | |
| Eagle2.5-8BAccess=Open weights2026.03 | 67 | |
| GPT-5 miniAccess=API call only2026.03 | 66.8 | |
| VideoChat-Flash-7BAccess=Fully open2026.03 | 66.4 | |
| PLM-3BAccess=Fully open2026.03 | 66.3 | |
| Qwen3-VL-8BAccess=Open weights2026.03 | 65.3 | |
| GLM-4.1V-9BAccess=Open weights2026.03 | 64.2 | |
| Qwen3-VL-4BAccess=Open weights2026.03 | 63.7 | |
| InternVL3.5-8BAccess=Open weights2026.03 | 63 | |
| Claude Sonnet 4.5Access=API call only2026.03 | 62.8 | |
| MiniCPM-V-4.5-8BAccess=Open weights2026.03 | 62.1 | |
| InternVL3.5-4BAccess=Open weights2026.03 | 62 | |
| Keye-VL-1.5-8BAccess=Open weights2026.03 | 60.1 | |
| LLaVA-Video-7BAccess=Fully open2026.03 | 59.4 |