| Qwen3.5: Towards Native Multimodal Agents | ✓ Link | 93.7 | Qwen3.5-397B-A17B | 2026-02-16 |
| Qwen3.5: Towards Native Multimodal Agents | ✓ Link | 92.8 | Qwen3.5-122B-A10B | 2026-02-16 |
| Qwen3.6 | ✓ Link | 92.8 | Qwen3.6-35B-A3B | 2026-04-21 |
| Qwen3.5: Towards Native Multimodal Agents | ✓ Link | 92.6 | Qwen3.5-27B | 2026-02-16 |
| Qwen3.6 | ✓ Link | 92.3 | Qwen3.6-27B | 2026-04-21 |
| Qwen3.5: Towards Native Multimodal Agents | ✓ Link | 91.5 | Qwen3.5-35B-A3B | 2026-02-16 |
| Qwen3.5: Towards Native Multimodal Agents | ✓ Link | 90.1 | Qwen3.5-9B | 2026-02-16 |
| GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning | ✓ Link | 88.8 | GLM-4.6V | 2025-07-01 |
| Qwen2.5-VL Technical Report | ✓ Link | 88.4 | Qwen2.5-VL-72B | 2025-02-19 |
| InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models | ✓ Link | 87.7 | InternVL3-78B | 2025-04-14 |
| Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution | ✓ Link | 85.9 | Qwen2-VL-72B | 2024-09-18 |
| Qwen3-VL Technical Report | ✓ Link | 85.0 | Qwen3-VL-8B-Instruct | 2025-11-26 |
| Ovis2.5 Technical Report | ✓ Link | 84.9 | Ovis2.5-9B | 2025-08-15 |
| Kimi-VL Technical Report | ✓ Link | 84.4 | Kimi-VL-A3B-Thinking-2506 | 2025-04-10 |
| MiniCPM-V 4.5: Cooking Efficient MLLMs via Architecture, Data, and Training Recipe | ✓ Link | 84.2 | MiniCPM-V 4.5 | 2025-09-16 |
| Language-guided Frequency Modulation for Large Vision-Language Models | | 84.2 | LFM (w/ Qwen2.5-VL) | 2026-06-03 |
| Kimi-VL Technical Report | ✓ Link | 83.1 | Kimi-VL-A3B-Instruct | 2025-04-10 |
| Qwen2.5-VL Technical Report | ✓ Link | 82.6 | Qwen2.5-VL-7B | 2025-02-19 |
| Qwen2.5-Omni Technical Report | ✓ Link | 81.8 | Qwen2.5-Omni-7B | 2025-03-26 |
| VisionFoundry: Teaching VLMs Visual Perception with Synthetic Images | ✓ Link | 81.6 | MiMo-VL-7B-SFT + VisionFoundry-10K | 2026-04-10 |
| Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution | ✓ Link | 80.7 | Qwen2-VL-7B | 2024-09-18 |
| COOPER: A Unified Model for Cooperative Perception and Reasoning in Spatial Intelligence | ✓ Link | 80.55 | COOPER | 2025-12-04 |
| Aria: An Open Multimodal Native Mixture-of-Experts Model | ✓ Link | 80.3 | Aria | 2024-10-08 |
| NGM: A Plug-and-Play Training-Free Memory Module for LLMs | ✓ Link | 76.63 | Qwen3-VL-2B + NGM | 2026-05-16 |
| Differences That Matter: Auditing Models for Capability Gap Discovery and Rectification | | 75.0 | Gemma3 + AuditDM | 2025-12-18 |
| Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution | ✓ Link | 72.2 | Qwen2-VL-2B | 2024-09-18 |