‹ PublicAI Index
The LLM benchmark aggregator.
MinerU2.5 1.2B
Other · 1.2B
Strongest in Document parsing (#61 of 76), weakest in Knowledge (#167 of 190). Above par in 0 of 2 scopes. Among the models it meets almost everywhere, it finishes behind Claude Opus 5.5 and Claude Fable 5.1 and ahead of OvisOCR2 and GPT-5.4 Nano.
§ 1 · Profile
What it is good at
Bars run from 50 — the average of the models each source lists — so right of the line is above par. The middle column is the gap to whoever leads that scope.
Knowledge42−20.8#167/1901/3
Document parsing41.4−22.3#61/761/1
§ 2 · Head to head
What it beats, and what beats it
The same models turn up scope after scope. Counted once: where both were placed, who finished higher. Bars run right for MinerU2.5 1.2B, left for the other.
§ 3 · Sources
Where the numbers come from
1 publication, 6 figures. Every one links to the page it was read from.
ParseBench · Overall 45.9%ParseBench · Tables 71.7%ParseBench · Charts 1.1%ParseBench · Content faithfulness 80.8%ParseBench · Semantic formatting 4.5%ParseBench · Visual grounding 71.5%
Badge
[](https://publicai.io/model-index/m/mineru2-5-1-2b)