Benchmark
OCRBench-V2 (zh)
OCR benchmarks measure how well models read text in images and documents. Scores are percentages.
All OCR benchmarksScores from LLM Stats data.
- Models measured
- 6
- Scores recorded
- 8
- Sources
- 1
- IQ weight
- 0.44
Score distribution
- 60.7%
- Mean
- 61.2%
- Median
- 1.7%
- Std dev
- 59.2%
- 10th percentile
- 62.1%
- 90th percentile
- 57.8%
- Min
This benchmark has a weight of 0.44 for chat models, measured over 6 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.
Leaderboard
| # | Model | Score |
|---|---|---|
| 1 | Qwen3 VL 235Bthinking· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. | 63.5% |
| 2 | Qwen3 VL 32B Thinking· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. | 62.1% |
| 3 | Qwen3 VL 235B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. | 61.8% |
| 4 | Qwen3 VL 8B Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. | 61.2% |
| 5 | qwen3-vl-30bthinking· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. | 60.4% |
| 6 | Qwen: Qwen3 VL 8B Thinking· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. | 59.2% |
| 7 | Qwen3 VL 32B Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. | 59.2% |
| 8 | qwen3-vl-30b· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. | 57.8% |
Data credits: Data by LLM Stats