AI benchmarks and leaderboards are different things
Learn the difference between a benchmark, an evaluation run and a leaderboard, and use each to answer the right question.
LLM Stats
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
Evaluation context and evidence
- Source
- LLM Stats
- Publisher
- Not recorded
- Benchmark release
- 2024-01-17
- Collected
- 2026-08-17
- Modality
- multimodal
These are source-reported observations, not independent reruns by this site. Check the task version, evaluation protocol, unit and reporting date before comparing models. Results from different setups are not a universal ranking.
Original sources
Reported results 24
Shown in source observation order, not ranked. Dates retain the precision provided by the source.
| Model | Value | Unit | Protocol | Reported date and basis | Source |
|---|---|---|---|---|---|
| Kimi K2.5 | 0.923 | Not recorded | Not recorded | 2026-01-27 · model_announcement | LLM Stats |
| Qwen3.5-122B-A10B | 0.921 | Not recorded | Not recorded | 2026-02-24 · model_announcement | LLM Stats |
| Qwen3 VL 235B A22B Instruct | 0.92 | Not recorded | Not recorded | 2025-09-22 · model_announcement | LLM Stats |
| Qwen3.5-35B-A3B | 0.91 | Not recorded | Not recorded | 2026-02-24 · model_announcement | LLM Stats |
| Qwen3 VL 30B A3B Instruct | 0.903 | Not recorded | Not recorded | 2025-09-22 · model_announcement | LLM Stats |
| Qwen3 VL 8B Instruct | 0.896 | Not recorded | Not recorded | 2025-09-22 · model_announcement | LLM Stats |
| Qwen3 VL 32B Instruct | 0.895 | Not recorded | Not recorded | 2025-09-22 · model_announcement | LLM Stats |
| Qwen3.6-27B | 0.894 | Not recorded | Not recorded | 2026-04-21 · model_announcement | LLM Stats |
| Qwen3.5-27B | 0.894 | Not recorded | Not recorded | 2026-02-24 · model_announcement | LLM Stats |
| Qwen2.5 VL 72B Instruct | 0.885 | Not recorded | Not recorded | 2025-01-26 · model_announcement | LLM Stats |
| Qwen3 VL 4B Instruct | 0.881 | Not recorded | Not recorded | 2025-09-22 · model_announcement | LLM Stats |
| Qwen2-VL-72B-Instruct | 0.877 | Not recorded | Not recorded | 2024-08-29 · model_announcement | LLM Stats |
| Qwen3 VL 235B A22B Thinking | 0.875 | Not recorded | Not recorded | 2025-09-22 · model_announcement | LLM Stats |
| Qwen2.5 VL 7B Instruct | 0.864 | Not recorded | Not recorded | 2025-01-26 · model_announcement | LLM Stats |
| Qwen3 VL 32B Thinking | 0.855 | Not recorded | Not recorded | 2025-09-22 · model_announcement | LLM Stats |
| Phi-4-multimodal-instruct | 0.844 | Not recorded | Not recorded | 2025-02-01 · model_announcement | LLM Stats |
| LFM2.5-VL-3B | 0.842 | Not recorded | Not recorded | 2026-08-12 · model_announcement | LLM Stats |
| Qwen3 VL 30B A3B Thinking | 0.839 | Not recorded | Not recorded | 2025-09-22 · model_announcement | LLM Stats |
| DeepSeek VL2 Small | 0.834 | Not recorded | Not recorded | 2024-12-13 · model_announcement | LLM Stats |
| Qwen3 VL 8B Thinking | 0.819 | Not recorded | Not recorded | 2025-09-22 · model_announcement | LLM Stats |
| DeepSeek VL2 | 0.811 | Not recorded | Not recorded | 2024-12-13 · model_announcement | LLM Stats |
| DeepSeek VL2 Tiny | 0.809 | Not recorded | Not recorded | 2024-12-13 · model_announcement | LLM Stats |
| Qwen3 VL 4B Thinking | 0.808 | Not recorded | Not recorded | 2025-09-22 · model_announcement | LLM Stats |
| North Micro Vision Instruct | 0.792 | Not recorded | Not recorded | 2026-08-12 · model_announcement | LLM Stats |