‹ PublicAI Index
The LLM benchmark aggregator.
MinerU Diffusion V1 2.5B
Other · 2.5B
Strongest in Document parsing (#68 of 76), weakest in Knowledge (#182 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 Nova 2 Lite and Qwen3.5 9B.
§ 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.
Knowledge39.2−23.6#182/1901/3
Document parsing38.4−25.3#68/761/1
§ 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 MinerU Diffusion V1 2.5B, 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 42.63%ParseBench · Tables 66.51%ParseBench · Charts 1.19%ParseBench · Content faithfulness 69.46%ParseBench · Semantic formatting 1.46%ParseBench · Visual grounding 74.54%
Badge
[](https://publicai.io/model-index/m/mineru-diffusion-v1-2-5b)