← Benchmarks
OCRBench
OCRBench: Comprehensive evaluation benchmark for assessing Optical Character Recognition (OCR) capabilities in Large Multimodal Models across text recognition, scene text VQA, and document understanding tasks
id ocrbench · max 1 · 24 models reported
| # | Model | Score |
|---|---|---|
| 1 | Kimi K2.5 Moonshot AI · open | 0.92 |
| 2 | Qwen3.5-122B-A10B Alibaba Cloud / Qwen Team · open | 0.92 |
| 3 | Qwen3 VL 235B A22B Instruct Alibaba Cloud / Qwen Team · open | 0.92 |
| 4 | Qwen3.5-35B-A3B Alibaba Cloud / Qwen Team · open | 0.91 |
| 5 | Qwen3 VL 30B A3B Instruct Alibaba Cloud / Qwen Team · open | 0.90 |
| 6 | Qwen3 VL 8B Instruct Alibaba Cloud / Qwen Team · open | 0.90 |
| 7 | Qwen3 VL 32B Instruct Alibaba Cloud / Qwen Team · open | 0.90 |
| 8 | Qwen3.5-27B Alibaba Cloud / Qwen Team · open | 0.89 |
| 9 | Qwen3.6-27B Alibaba Cloud / Qwen Team · open | 0.89 |
| 10 | Qwen2.5 VL 72B Instruct Alibaba Cloud / Qwen Team · open | 0.89 |
| 11 | Qwen3 VL 4B Instruct Alibaba Cloud / Qwen Team · open | 0.88 |
| 12 | Qwen2-VL-72B-Instruct Alibaba Cloud / Qwen Team · open | 0.88 |
| 13 | Qwen3 VL 235B A22B Thinking Alibaba Cloud / Qwen Team · open | 0.88 |
| 14 | Qwen2.5 VL 7B Instruct Alibaba Cloud / Qwen Team · open | 0.86 |
| 15 | Qwen3 VL 32B Thinking Alibaba Cloud / Qwen Team · open | 0.85 |