Codesota · Models · MinerU2.52 results · 2 benchmarks
Model card

MinerU2.5.

unknown
§ 02 · Benchmarks

Every benchmark MinerU2.5 has a recorded score for.

#BenchmarkArea · TaskMetricValueRankDateSource
01OmniDocBenchComputer Vision · Document Parsingaccuracy90.7%#7/13—source ↗
02olmOCR-BenchComputer Vision · Document Parsingaccuracy77.5%#12/18—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.
§ 03 · Strengths by area

Where MinerU2.5 actually performs.

Computer Vision
2
benchmarks
avg rank #9.5
§ 04 · Papers

1 paper with results for MinerU2.5.

  1. 2025-09-26· 2 results

    MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing

§ 06 · Sources & freshness

Where these numbers come from.

pwc-dump
2
results
0 of 2 rows marked verified.