Benchmark
OCRBench-V2 (zh)
What is OCRBench-V2 (zh)?
OCRBench v2 Chinese subset: Enhanced benchmark for evaluating Large Multimodal Models on visual text localization and reasoning with Chinese text content
- Modality
- multimodal
- Evaluates
- image to text, vision
- Openness
- unknown
- Importer
- LLM Stats
- Reported scores
- 11
Source provenance
OCRBench-V2 (zh) results and reported scores
LLM Stats
| Model | Organization | Reported value | Reported | Evidence |
|---|---|---|---|---|
| Qwen2.5 VL 32B Instruct | Qwen | 0.591 | 2025-02-28 | evidence |
| Qwen3 VL 235B A22B Instruct | Qwen | 0.618 | 2025-09-22 | evidence |
| Qwen3 VL 235B A22B Thinking | Qwen | 0.635 | 2025-09-22 | evidence |
| Qwen3 VL 30B A3B Instruct | Qwen | 0.578 | 2025-09-22 | evidence |
| Qwen3 VL 30B A3B Thinking | Qwen | 0.604 | 2025-09-22 | evidence |
| Qwen3 VL 32B Instruct | Qwen | 0.592 | 2025-09-22 | evidence |
| Qwen3 VL 32B Thinking | Qwen | 0.621 | 2025-09-22 | evidence |
| Qwen3 VL 4B Instruct | Qwen | 0.576 | 2025-09-22 | evidence |
| Qwen3 VL 4B Thinking | Qwen | 0.558 | 2025-09-22 | evidence |
| Qwen3 VL 8B Instruct | Qwen | 0.612 | 2025-09-22 | evidence |
| Qwen3 VL 8B Thinking | Qwen | 0.592 | 2025-09-22 | evidence |
Scores are partitioned by the source that reported them and are never merged into a single cross-source ranking, because the sources measure different things and say so.