| STEP3-VL-10B Technical Report | ✓ Link | 91.96 | Step3-VL-10B (PaCoRe) | 2026-01-14 |
| HopChain: Multi-Hop Data Synthesis for Generalizable Vision-Language Reasoning | | 91.72 | Qwen3.5-397B-A17B (RLVR w/ Multi-Hop) | 2026-03-17 |
| ERNIE 4.5 Technical Report | ✓ Link | 90.9 | ERNIE-4.5-VL-424B-A47B | 2025-06-30 |
| Qwen3-VL Technical Report | ✓ Link | 88.9 | Qwen3-VL-235B-A22B-Instruct | 2025-11-26 |
| InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models | ✓ Link | 88.7 | InternVL3-78B | 2025-04-14 |
| GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning | ✓ Link | 88.2 | GLM-4.6V | 2025-07-01 |
| Step-GUI Technical Report | ✓ Link | 88.0 | Step-GUI-8B | 2025-12-17 |
| Qwen2.5-VL Technical Report | ✓ Link | 87.9 | Qwen2.5-VL-72B | 2025-02-19 |
| Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution | ✓ Link | 86.6 | Qwen2-VL-72B | 2024-09-18 |
| LLaVA-UHD v4: What Makes Efficient Visual Encoding in MLLMs? | ✓ Link | 86.5 | LLaVA-UHD v4 | 2026-05-09 |
| Language-guided Frequency Modulation for Large Vision-Language Models | | 84.7 | LFM (w/ Qwen2.5-VL) | 2026-06-03 |
| Unfold The World: Factorize 4D Properties in Reinforcing Spatial Reasoning | ✓ Link | 84.1 | FactoSR-8B-RL | 2026-09-03 |
| Unlocking Dense Metric Depth Estimation in VLMs | ✓ Link | 82.3 | DepthVLM-8B | 2026-05-15 |
| LLaDA2.0-Uni: Unifying Multimodal Understanding and Generation with Diffusion Large Language Model | ✓ Link | 81.2 | LLaDA2.0-Uni (16B) | 2026-04-22 |
| A Pocket-Sized MLLM for Ultra-Efficient Image and Video Understanding on Your Phone | | 81.0 | MiniCPM-V 4.6-Thinking (16x) | 2026-05-13 |
| Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution | ✓ Link | 80.5 | Qwen2-VL-7B | 2024-09-18 |
| LLaVA-NeXT: Improved reasoning, OCR, and world knowledge | ✓ Link | 79 | LLaVA-NeXT-34B | 2024-01-30 |
| LLaDA-UI: Bringing Block-wise Diffusion to Vision-Language GUI Agents | ✓ Link | 77.7 | LLaDA-UI (pre-training) | 2026-09-09 |
| Ovis: Structural Embedding Alignment for Multimodal Large Language Model | ✓ Link | 76.6 | Ovis-Qwen1.5-14B | 2024-05-31 |
| MiniCPM-V: A GPT-4V Level MLLM on Your Phone | ✓ Link | 74.2 | MiniCPM-Llama3-V 2.5 | 2024-08-03 |
| Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution | ✓ Link | 73.5 | Qwen2-VL-2B | 2024-09-18 |
| DeepSeek-VL: Towards Real-World Vision-Language Understanding | ✓ Link | 72.8 | DeepSeek-VL 7B Chat | 2024-03-08 |
| Token-level Response-visual Attention Guidance for Multimodal LLMs Knowledge Distillation | ✓ Link | 69.3 | TRAG (Qwen2.5-1.5B) | 2026-07-01 |
| Improved Baselines with Visual Instruction Tuning | ✓ Link | 58.3 | LLaVA-1.5-7B | 2023-10-05 |