| Qwen3.5: Towards Native Multimodal Agents | ✓ Link | 71.4 | Qwen3.5-397B-A17B | 2026-02-16 |
| Qwen3.5: Towards Native Multimodal Agents | ✓ Link | 70.0 | Qwen3.5-27B | 2026-02-16 |
| Qwen3.5: Towards Native Multimodal Agents | ✓ Link | 69.3 | Qwen3.5-9B | 2026-02-16 |
| Qwen3.5: Towards Native Multimodal Agents | ✓ Link | 67.9 | Qwen3.5-35B-A3B | 2026-02-16 |
| Qwen3.5: Towards Native Multimodal Agents | ✓ Link | 67.6 | Qwen3.5-122B-A10B | 2026-02-16 |
| Kwai Keye-VL Technical Report | ✓ Link | 67.0 | Keye-VL-8B | 2025-07-02 |
| Qwen3-VL Technical Report | ✓ Link | 66.7 | Qwen3-VL-235B-A22B-Thinking | 2025-11-26 |
| Ovis2.5 Technical Report | ✓ Link | 65.1 | Ovis2.5-9B | 2025-08-15 |
| Generation Enhances Understanding in Unified Multimodal Models via Multi-Representation Generation | ✓ Link | 64.56 | OpenUni-3.6B + UniMRG | 2026-01-29 |
| Qwen3-Omni Technical Report | ✓ Link | 63.4 | Qwen3-Omni-Flash-Thinking | 2025-09-22 |
| MiniCPM-o 4.5: Towards Real-Time Full-Duplex Omni-Modal Interaction | ✓ Link | 63.2 | MiniCPM-o 4.5-Instruct | 2026-04-30 |
| Kwai Keye-VL 1.5 Technical Report | ✓ Link | 62.7 | Keye-VL-1.5-8B | 2025-09-01 |
| GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning | ✓ Link | 62.3 | GLM-4.6V | 2025-07-01 |
| MiniCPM-V 4.5: Cooking Efficient MLLMs via Architecture, Data, and Training Recipe | ✓ Link | 61.2 | MiniCPM-V 4.5 | 2025-09-16 |
| From Pixels to Words -- Towards Native One-Vision Models at Scale | ✓ Link | 59.8 | NEO-ov 9B | 2026-05-27 |
| InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models | ✓ Link | 59.1 | InternVL3-78B | 2025-04-14 |
| Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution | ✓ Link | 58.1 | Qwen2-VL-72B | 2024-09-18 |
| Envision, Attend, Then Respond: Counterfactual Hallucination Mitigation in Large Vision-Language Models | ✓ Link | 56.82 | EnAR (Qwen2.5VL-7B) | 2026-06-03 |
| Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution | ✓ Link | 50.6 | Qwen2-VL-7B | 2024-09-18 |
| From Pixels to Words -- Towards Native Vision-Language Primitives at Scale | ✓ Link | 46.4 | NEO-9B | 2025-10-16 |
| LoopVL: Recurrent Visual Intelligence | ✓ Link | 44.71 | LoopVL-1B | 2026-09-29 |
| Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution | ✓ Link | 41.7 | Qwen2-VL-2B | 2024-09-18 |