Model card
MinerU 2.5.
OpenDataLabopen-sourceDocument extraction pipelineAGPL-3.01 current SOTA
#1 on layout detection (97.5 mAP)
§ 01 · Benchmarks
Every benchmark MinerU 2.5 has a recorded score for.
| # | Benchmark | Area · Task | Metric | Value | Rank | Date | Source |
|---|---|---|---|---|---|---|---|
| 01 | OmniDocBench | Computer Vision · Document Parsing | layout-map | 97.5% | #1 | — | source ↗ |
| 02 | OmniDocBench | Computer Vision · Document Parsing | composite | 90.7% | #6 | — | source ↗ |
| 03 | olmOCR-Bench | Computer Vision · Document Parsing | pass-rate | 75.2% | #17 | — | source ↗ |
Rank column shows this model’s position vs all other models scored on the same benchmark + metric (competitors after the slash). #1 in red means current SOTA. Sorted by rank, then newest result.
§ 02 · Strengths by area
Where MinerU 2.5 actually performs.
§ 04 · Related models
Other OpenDataLab models scored on Codesota.
§ 05 · Sources & freshness
Where these numbers come from.
alphaxiv-leaderboard
2
results
AlphaXiv
1
result
0 of 3 rows marked verified.