Benchmark
ParseBench
Scores are percentages. Higher is better.
Scores from Hugging Face Official Benchmarks data, LLM Stats data.
- Models measured
- 16
- Scores recorded
- 16
- Sources
- 2
- IQ weight
- 0.84
Score distribution
- 56.8%
- Mean
- 56.6%
- Median
- 14.4%
- Std dev
- 44.1%
- 10th percentile
- 75.1%
- 90th percentile
- 29.6%
- Min
This benchmark has a weight of 0.84 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 | Parse V5.0· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 79.2% |
| 2 | LightOnOCR-3 4B· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim | 75.1% |
| 3 | Lightonocr 3 0.8b· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim | 74.6% |
| 4 | Qwen 3.8 27B· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim | 70.8% |
| 5 | GLM 5.3 Flash· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim | 70.8% |
| 6 | PaddleOCR-VL-1.6· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim | 67.4% |
| 7 | HunyuanOCR· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim | 63.9% |
| 8 | DeepSeek V4.1 Flash· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim | 56.6% |
| 9 | Nemotron 3 Nano Omni 30b A3b Reasoning· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim | 48.5% |
| 10 | LightOnOCR-2-1B· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim | 48% |
| 11 | Qwen3 VL 8B Instruct· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim | 46.8% |
| 12 | Qianfan-OCR· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim | 46.2% |
| 13 | Jina OCR v1· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim | 45.9% |
| 14 | Qwen3.6 35B A3B· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim | 44.1% |
| 15 | DeepSeek OCR 2· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim | 41.2% |
| 16 | GLM OCR· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim | 29.6% |
Data credits: Hugging Face official benchmark leaderboards; licence varies by benchmark · Data by LLM Stats