| Paper | Code | Accuracy | ModelName | ReleaseDate |
|---|---|---|---|---|
| InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models | ✓ Link | 73.2 | InternVL3-78B | 2025-04-14 |
| MiniCPM-o 4.5: Towards Real-Time Full-Duplex Omni-Modal Interaction | ✓ Link | 69.7 | MiniCPM-o 4.5-Instruct | 2026-04-30 |
| Ovis2.5 Technical Report | ✓ Link | 69.3 | Ovis2.5-9B | 2025-08-15 |
| MiniCPM-V 4.5: Cooking Efficient MLLMs via Architecture, Data, and Training Recipe | ✓ Link | 68.3 | MiniCPM-V 4.5 | 2025-09-16 |
| OneThinker: All-in-one Reasoning Model for Image and Video | ✓ Link | 67.8 | OneThinker-8B | 2025-12-02 |
| CoLT: Teaching Multi-Modal Models to Think with Chain of Latent Thoughts | ✓ Link | 67.4 | CoLT | 2026-06-30 |
| Differences That Matter: Auditing Models for Capability Gap Discovery and Rectification | 58.9 | Gemma3 + AuditDM | 2025-12-18 |