OCRBench-V2 (zh)
OCRBench v2 Chinese subset: Enhanced benchmark for evaluating Large Multimodal Models on visual text localization and reasoning with Chinese text content
11rows
scoreprimary metric
2026-05-06sampled
Metadata
Metrics
Score, Normalized Score
| Rank | Subject | Score | Model Match | Provenance | Sampled |
|---|---|---|---|---|---|
| 1 | Qwen3 VL 235B A22B Thinking | 0.64 |  Qwen3 VL 235B A22B Thinking qwen-qwen3-vl-235b-a22b-thinking | Self-reported | 2026-05-06 |
| 2 | Qwen3 VL 32B Thinking | 0.62 | — | Self-reported | 2026-05-06 |
| 3 | Qwen3 VL 235B A22B Instruct | 0.62 | Qwen3 VL 235B A22B Instruct qwen-qwen3-vl-235b-a22b-instruct | Self-reported | 2026-05-06 |
| 4 | Qwen3 VL 8B Instruct | 0.61 | Qwen3 VL 8B Instruct qwen-qwen3-vl-8b-instruct | Self-reported | 2026-05-06 |
| 5 | Qwen3 VL 30B A3B Thinking | 0.60 | Qwen3 VL 30B A3B Thinking qwen-qwen3-vl-30b-a3b-thinking | Self-reported | 2026-05-06 |
| 6 | Qwen3 VL 8B Thinking | 0.59 | Qwen3 VL 8B Thinking qwen-qwen3-vl-8b-thinking | Self-reported | 2026-05-06 |
| 6 | Qwen3 VL 32B Instruct | 0.59 | Qwen3 VL 32B Instruct qwen-qwen3-vl-32b-instruct | Self-reported | 2026-05-06 |
| 8 | Qwen2.5 VL 32B Instruct | 0.59 | — | Self-reported | 2026-05-06 |
| 9 | Qwen3 VL 30B A3B Instruct | 0.58 | Qwen3 VL 30B A3B Instruct qwen-qwen3-vl-30b-a3b-instruct | Self-reported | 2026-05-06 |
| 10 | Qwen3 VL 4B Instruct | 0.58 | — | Self-reported | 2026-05-06 |
| 11 | Qwen3 VL 4B Thinking | 0.56 | — | Self-reported | 2026-05-06 |
No matching rows.