Benchmark
OCRBench-V2 (en)
What is OCRBench-V2 (en)?
OCRBench v2 English subset: Enhanced benchmark for evaluating Large Multimodal Models on visual text localization and reasoning with English text content
- Modality
- multimodal
- Evaluates
- image to text, vision
- Openness
- unknown
- Importer
- LLM Stats
- Reported scores
- 14
Source provenance
OCRBench-V2 (en) results and reported scores
LLM Stats
| Model | Organization | Reported value | Reported | Evidence |
|---|---|---|---|---|
| LFM2.5-VL-3B | Liquid AI | 0.475 | 2026-08-12 | evidence |
| North Micro Vision Instruct | Cohere | 0.367 | 2026-08-12 | evidence |
| Qwen2.5 VL 32B Instruct | Qwen | 0.572 | 2025-02-28 | evidence |
| Qwen2.5 VL 72B Instruct | Qwen | 0.615 | 2025-01-26 | evidence |
| Qwen3 VL 235B A22B Instruct | Qwen | 0.671 | 2025-09-22 | evidence |
| Qwen3 VL 235B A22B Thinking | Qwen | 0.668 | 2025-09-22 | evidence |
| Qwen3 VL 30B A3B Instruct | Qwen | 0.632 | 2025-09-22 | evidence |
| Qwen3 VL 30B A3B Thinking | Qwen | 0.626 | 2025-09-22 | evidence |
| Qwen3 VL 32B Instruct | Qwen | 0.674 | 2025-09-22 | evidence |
| Qwen3 VL 32B Thinking | Qwen | 0.684 | 2025-09-22 | evidence |
| Qwen3 VL 4B Instruct | Qwen | 0.637 | 2025-09-22 | evidence |
| Qwen3 VL 4B Thinking | Qwen | 0.618 | 2025-09-22 | evidence |
| Qwen3 VL 8B Instruct | Qwen | 0.654 | 2025-09-22 | evidence |
| Qwen3 VL 8B Thinking | Qwen | 0.639 | 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.