| Paper | Code | Accuracy | ModelName | ReleaseDate |
|---|---|---|---|---|
| PerceptionLM: Open-Access Data and Models for Detailed Visual Understanding | ✓ Link | 82.7 | PLM-8B | 2025-04-17 |
| Molmo2: Open Weights and Data for Vision-Language Models with Video Understanding and Grounding | ✓ Link | 82.1 | Molmo2-8B | 2026-01-15 |
| VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding | ✓ Link | 72.8 | VideoLLaMA3 7B | 2025-01-22 |
| The Llama 3 Herd of Models | ✓ Link | 60.8 | Llama 3-V (70B) | 2024-07-31 |
| Gemini: A Family of Highly Capable Multimodal Models | ✓ Link | 54.7 | Gemini Ultra | 2023-12-19 |