| Qianfan-OCR: A Unified End-to-End Model for Document Intelligence | ✓ Link | 94.0 | Qianfan-OCR | 2026-03-11 |
| Qwen3-VL Technical Report | ✓ Link | 90.5 | Qwen3-VL-235B-A22B-Thinking | 2025-11-26 |
| LongCat-Next: Lexicalizing Modalities as Discrete Tokens | ✓ Link | 89.9 | LongCat-Next (A3B, 68.5B) | 2026-03-29 |
| Nemotron 3 Nano Omni: Efficient and Open Multimodal Intelligence | ✓ Link | 88.9 | Nemotron 3 Nano Omni (Reasoning) | 2026-04-27 |
| Qwen2.5-VL Technical Report | ✓ Link | 87.4 | Qwen2.5-VL-72B | 2025-02-19 |
| Step-GUI Technical Report | ✓ Link | 86.3 | Step-GUI-8B | 2025-12-17 |
| Intern Lumina U2: A Multi-Codebook Diffusion Large Language Model for Omni-Visual Understanding and Image Generation | ✓ Link | 85.9 | Intern Lumina U2 (Ascend) | 2026-10-14 |
| InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models | ✓ Link | 85.1 | InternVL3-78B | 2025-04-14 |
| Twin-T & TwintVQA: A Reliable Structure-Detail Separating VLM and a Comprehensive Benchmark for Chart and Table Tasks | ✓ Link | 84.88 | Twin-T-7B | 2026-06-03 |
| Act Wisely: Cultivating Meta-Cognitive Tool Use in Agentic Multimodal Models | ✓ Link | 83.4 | Metis | 2026-04-09 |
| Penguin-VL: Exploring the Efficiency Limits of VLM with LLM-based Vision Encoders | ✓ Link | 83.0 | Penguin-VL 8B | 2026-03-06 |
| Youtu-VL: Unleashing Visual Potential via Unified Vision-Language Supervision | ✓ Link | 79.0 | Youtu-VL (4B) | 2026-01-27 |
| Generation as Auxiliary Supervision: Enhancing Visual Understanding at Zero Inference Overhead via Decoupled Embedding Prediction | | 78.4 | GAS (4B) | 2026-08-12 |
| Kwai Keye-VL Technical Report | ✓ Link | 77.7 | Keye-VL-8B | 2025-07-02 |
| Learning Consistency in Reward Modeling for Multi-Modal Reasoning | | 77.3 | Qwen2.5-VL-7B (CRM RL, after RL) | 2026-09-08 |
| Language-guided Frequency Modulation for Large Vision-Language Models | | 75.8 | LFM (w/ Qwen2.5-VL) | 2026-06-03 |
| LLaDA-UI: Bringing Block-wise Diffusion to Vision-Language GUI Agents | ✓ Link | 72.2 | LLaDA-UI (pre-training) | 2026-09-09 |
| LLaDA2.0-Uni: Unifying Multimodal Understanding and Generation with Diffusion Large Language Model | ✓ Link | 68.4 | LLaDA2.0-Uni (16B) | 2026-04-22 |
| Penguin-VL: Exploring the Efficiency Limits of VLM with LLM-based Vision Encoders | ✓ Link | 62.3 | Penguin-VL 2B | 2026-03-06 |