Is MiniCPM (OCR) superseded?

MiniCPM (OCR) (Retrieval-augmented generation): superseded — cited as a baseline and beaten by newer methods. 0 paper(s) critique it, 2 beat it on benchmarks — #102 of 1179 most-superseded. Sub-problem: cluster led by MMGraphRAG. Newer alternatives in the same sub-problem include VideoStir, Graph-to-Frame RAG, MG$^2$-RAG, AutoThinkRAG, AgenticOCR.

Method Drift›Retrieval-augmented generation

Superseded baseline#102 of 1,179 most-superseded

MiniCPM (OCR)

Retrieval-augmented generation

superseded — cited as a baseline and beaten by newer methods

0 papers critique it · 2 beat it on benchmarks

Beaten on benchmarks

Head-to-head results where a newer method reports beating MiniCPM (OCR). Values are copied from the source paper's tables — verify against the cited paper.

VisRAG-Ret beats MiniCPM (OCR) · Average MRR@10 [MLLMs as End-to-End Representers]
77.91 vs 74.78
Roles of MLLMs in Visually Rich Document Retrieval for RAG: A Survey
VisRAG-Ret beats MiniCPM (OCR) · Average MRR@10 [Out-of-domain: Models Fine-tuned on Synthetic Data]
69.17 vs 47.96
VisRAG: Vision-based Retrieval-augmented Generation on Multi-modality Documents
VisRAG-Ret beats MiniCPM (OCR) · Average MRR@10 [In-domain: Models Fine-tuned on Synthetic and In-domain data]
75.11 vs 58.43
VisRAG: Vision-based Retrieval-augmented Generation on Multi-modality Documents
VisRAG-Gen Page Concatenation beats MiniCPM (OCR) · Average accuracy top-1 [Text-based Generation with MiniCPM (OCR)]
36.16 vs 27.68
VisRAG: Vision-based Retrieval-augmented Generation on Multi-modality Documents

Newer alternatives

Recent methods in the same sub-problem, not yet superseded in the knowledge base.