‹ PublicAI Index
The LLM benchmark aggregator.
Qianfan OCR
Other
Strongest in Document parsing (#60 of 76), weakest in Knowledge (#165 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 MinerU2.5 1.2B and OvisOCR2.
§ 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.
Knowledge42.9−19.9#165/1901/3
Document parsing42.5−21.2#60/761/1
§ 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 Qianfan OCR, 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 46.2%ParseBench · Tables 72.3%ParseBench · Charts 0.9%ParseBench · Content faithfulness 83.5%ParseBench · Semantic formatting 53.8%ParseBench · Visual grounding 20.6%
Badge
[](https://publicai.io/model-index/m/qianfan-ocr)