MiniCPM-OCR-1.0 model card Oct 28, 2026
- OmniDocBench v1.6 96.5
- Real5-OmniDocBench 93.7
- Wild-OmniDocBench 92.4
- olmOCR-bench 82.7
- CHAOS-Bench 29.8
- OCRBench v2 54.7
MiniCPM-OCR-1.0 places in the top three on 2 benchmarks.
Open weights Small
Its best score on each benchmark, and where that ranks among every model with a score there. We rank each model once, at its best setting.
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| OmniDocBench v1.6 | 96.4 | #2 of 10 | Official leaderboard | |
| BHL OCR Eval | 3.68% | #2 of 8 | Official leaderboard | |
| ParseBench | 61.7% | #27 of 48 | Official leaderboard | |
| ParseBench-2 | 71% | #15 of 21 | Official leaderboard | |
| OmniParseBench | 83.5 | #9 of 12 | Official leaderboard | |
| Real5-OmniDocBench | 93.7% | #1 of 1 lab number | Lab model card | |
| Wild-OmniDocBench | 92.4% | #1 of 1 lab number | Lab model card | |
| CHAOS-Bench | 29.8% | Not ranked | Lab model card | |
| OCRBench v2 | 54.7% | Not ranked | Lab model card | |
| olmOCR-Bench | 82.7% | Not ranked | Lab model card |
Independent runs cover 5 of its 10 benchmarks. For the other 5, we have only OpenBMB (ModelBest)'s own number or a claim Epoch AI collected.
Sources: Official leaderboards, Epoch AI (CC BY 4.0) and labs’ model cards
The benchmarks the lab chose to headline, with the scores it gave.