Multimodal Video Evaluation on Video-MME (test)
88.6AccuracyGemini 3 Pro
Evaluation Results
| Method | Links | |
|---|---|---|
| Gemini 3 ProCategory=API call only2026.03 | 88.6 | |
| Gemini 2.5 ProCategory=API call only2026.03 | 87.8 | |
| Gemini 2.5 FlashCategory=API call only2026.03 | 84.2 | |
| GPT-5Category=API call only2026.03 | 83.3 | |
| GPT-5 miniCategory=API call only2026.03 | 77.3 | |
| Claude Sonnet 4.5Category=API call only2026.03 | 74.2 | |
| Keye-VL-1.5-8BCategory=Open weights2026.03 | 73 | |
| Eagle2.5-8BCategory=Open weights2026.03 | 72.4 | |
| Qwen3-VL-8BCategory=Open weights2026.03 | 71.4 | |
| Molmo2-8BCategory=Fully open2026.03 | 69.9 | |
| Molmo2-4BCategory=Fully open2026.03 | 69.6 | |
| MolmoPoint-8BCategory=MolmoPoint2026.03 | 69.6 | |
| Qwen3-VL-4BCategory=Open weights2026.03 | 69.3 | |
| GLM-4.1V-9BCategory=Open weights2026.03 | 68.2 | |
| MiniCPM-V-4.5-8BCategory=Open weights2026.03 | 67.9 | |
| InternVL3.5-8BCategory=Open weights2026.03 | 66 | |
| InternVL3.5-4BCategory=Open weights2026.03 | 65.4 | |
| VideoChat-Flash-7BCategory=Fully open2026.03 | 65.3 | |
| Molmo2-O-7BCategory=Fully open2026.03 | 64.9 | |
| LLaVA-Video-7BCategory=Fully open2026.03 | 63.3 | |
| PLM-8BCategory=Fully open2026.03 | 58.3 | |
| PLM-3BCategory=Fully open2026.03 | 54.9 |