Benchmark
OCRBench_V2
vision
image-to-text
multimodal
多语言
OCRBench v2: Enhanced large-scale bilingual benchmark for evaluating Large Multimodal Models on visual text localization and reasoning with 10,000 human-verified question-answering pairs across 8 core OCR capabilities
语言EN
满分1
参评模型1
模型排名
| 名次 | 模型 | 机构 | 分数 | 来源 |
|---|---|---|---|---|
| 1 | Qwen2.5-Omni-7B | Alibaba Cloud / Qwen Team | 57.8 | 来源 ↗ |