| GLM-OCR Technical Report | ✓ Link | 94.62 | GLM-OCR | 2026-03-11 |
| PaddleOCR-VL-1.5: Towards a Multi-Task 0.9B VLM for Robust In-the-Wild Document Parsing | ✓ Link | 94.5 | PaddleOCR-VL-1.5 | 2026-01-29 |
| RT-DocLayout: Real-Time End-to-End Document Layout Analysis with Reading Order in the Wild | ✓ Link | 94.50 | RT-DocLayout + PaddleOCR-VL-1.5-0.9B | 2026-06-22 |
| HunyuanOCR Technical Report | ✓ Link | 94.10 | HunyuanOCR | 2025-11-24 |
| Unlimited OCR Works | ✓ Link | 93.23 | Unlimited-OCR | 2026-06-22 |
| Qianfan-OCR: A Unified End-to-End Model for Document Intelligence | ✓ Link | 93.12 | Qianfan-OCR | 2026-03-11 |
| FireRed-OCR Technical Report | ✓ Link | 92.94 | FireRed-OCR-2B | 2026-03-02 |
| Boosting Document Parsing Efficiency and Performance with Coarse-to-Fine Visual Processing | ✓ Link | 92.62 | PaddleOCR-VL-L | 2026-03-25 |
| Qwen3.8-Max: A New Bar for Coding and Cowork | ✓ Link | 92.1 | Qwen3.8-Max | 2026-08-03 |
| MiniMax M3: Frontier Coding, 1M Context, Native Multimodality — All in One Model | ✓ Link | 91.6 | MiniMax M3 | 2026-05-31 |
| Qwen3.8-27B | ✓ Link | 91.1 | Qwen3.8-27B | 2026-08-05 |
| Qwen3.5: Towards Native Multimodal Agents | ✓ Link | 90.8 | Qwen3.5-397B-A17B | 2026-02-16 |
| MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing | ✓ Link | 90.67 | MinerU2.5 | 2025-09-26 |
| Qwen3.5: Towards Native Multimodal Agents | ✓ Link | 89.8 | Qwen3.5-122B-A10B | 2026-02-16 |
| Qwen3.5: Towards Native Multimodal Agents | ✓ Link | 89.3 | Qwen3.5-35B-A3B | 2026-02-16 |
| MinerU-Diffusion: Rethinking Document OCR as Inverse Rendering via Diffusion Decoding | ✓ Link | 88.94 | MinerU-Diffusion | 2026-03-23 |
| Qwen3.5: Towards Native Multimodal Agents | ✓ Link | 88.9 | Qwen3.5-27B | 2026-02-16 |
| Qwen3.5: Towards Native Multimodal Agents | ✓ Link | 87.7 | Qwen3.5-9B | 2026-02-16 |
| DARL: Efficient Document-to-Markup Generation via Look-Ahead Diffusion Trajectory Sampling | | 87.69 | DARL (extra data) | 2026-09-08 |
| Kwai Keye-VL-2.0 Technical Report | ✓ Link | 84.7 | Keye-VL-2.0-30B-A3B | 2026-06-09 |
| A Pocket-Sized MLLM for Ultra-Efficient Image and Video Understanding on Your Phone | | 84.6 | MiniCPM-V 4.6 (Instruct, 4x) | 2026-05-13 |
| FastOCR: Dynamic Visual Fixation via KV Cache Pruning for Efficient Document Parsing | | 84.31 | FastOCR + dots.ocr (tau=0.25) | 2026-05-17 |
| EXAONE 4.5 Technical Report | ✓ Link | 81.2 | EXAONE 4.5 (Reasoning) | 2026-04-09 |