Codesota · Benchmark · pendigitsHome/Leaderboards/Vision & Documents/Document OCR/pendigits
Unknown

pendigits.

pendigits is a state-of-the-art machine learning benchmark indexed on Codesota. This page tracks published model results, top scores per metric, and the SOTA timeline for pendigits.

Paper ↗Leaderboard ↓
§ 01 · SOTA history

Year over year.

§ 02 · Leaderboard

Results by metric.

Found a wrong score or missing run?
Use row edits to send a sourced correction into moderation.
Add / edit result ↗Report issue ↗

Nmi

Nmi is the reported evaluation metric for pendigits. Codesota tracks published model scores on this metric so readers can compare state-of-the-art results across sources and model families.

Higher is better

Trust tiers for Nmiverifiedpapervendorcommunityunverified
RankModelTrustScoreYearLinksFix
01DnC-SC
From paper: Divide-and-conquer based Large-Scale Spectral Clustering
verified82.862021Paper ↗Code ↗Looks wrong?
02U-SPEC
From paper: Ultra-Scalable Spectral Clustering and Ensemble Clustering
verified81.682021Paper ↗Code ↗Source ↗Looks wrong?
03LSC-K
From paper: Divide-and-conquer based Large-Scale Spectral Clustering
verified81.372021Paper ↗Code ↗Looks wrong?
04ASNMF-SRP
From Table in Entropy (Basel) 2025 (DOI: 10.3390/e27080875). Pendigits dataset. ASNMF-SRP achieves 80.12% NMI, best among NMF-based methods compared. Note: stored as percentage.
verified80.122025Paper ↗Looks wrong?
05LSC-R
From paper: Divide-and-conquer based Large-Scale Spectral Clustering
verified79.152021Paper ↗Code ↗Looks wrong?

Accuracy

Accuracy is the reported evaluation metric for pendigits. Codesota tracks published model scores on this metric so readers can compare state-of-the-art results across sources and model families.

Higher is better

Trust tiers for Accuracyverifiedpapervendorcommunityunverified
RankModelTrustScoreYearLinksFix
01DnC-SC
From paper: Divide-and-conquer based Large-Scale Spectral Clustering
verified82.272021Paper ↗Code ↗Looks wrong?
02U-SPEC
From paper: Divide-and-conquer based Large-Scale Spectral Clustering
verified81.682021Paper ↗Code ↗Looks wrong?
03LSC-R
From paper: Divide-and-conquer based Large-Scale Spectral Clustering
verified81.552021Paper ↗Code ↗Looks wrong?
04ASNMF-SRP
From Table in Entropy (Basel) 2025 (DOI: 10.3390/e27080875). Pendigits dataset. ASNMF-SRP achieves 80.44% ACC, best among NMF-based methods compared.
verified80.442025Paper ↗Looks wrong?
05RCC
From Table 2 of DPAC (ECCV 2024). Pendigits: 10,992 samples, 16 dims, 10 classes. RCC accuracy: 79.6±0.0. RCC is designed for entangled data.
verified79.62024Paper ↗Looks wrong?
06PAC
From Table 2 of DPAC (ECCV 2024). Pendigits: 10,992 samples, 16 dims, 10 classes. PAC accuracy: 78.0±0.0.
verified782024Paper ↗Looks wrong?
07LBDM
From paper: Large-scale spectral clustering using diffusion coordinates on landmark-based bipartite graphs
verified74.72018Paper ↗Looks wrong?
08LSC-K
From paper: Divide-and-conquer based Large-Scale Spectral Clustering
verified74.022021Paper ↗Code ↗Looks wrong?

Ari

Ari is the reported evaluation metric for pendigits. Codesota tracks published model scores on this metric so readers can compare state-of-the-art results across sources and model families.

Higher is better

Trust tiers for Ariverifiedpapervendorcommunityunverified
RankModelTrustScoreYearLinksFix
01ASNMF-SRP
From Table in Entropy (Basel) 2025 (DOI: 10.3390/e27080875). Pendigits dataset. ASNMF-SRP achieves 68.49% ARI, best among NMF-based methods compared. Note: stored as percentage.
verified68.492025Paper ↗Looks wrong?

Runtime S

Runtime S is the reported evaluation metric for pendigits. Codesota tracks published model scores on this metric so readers can compare state-of-the-art results across sources and model families.

Higher is better

Trust tiers for Runtime Sverifiedpapervendorcommunityunverified
RankModelTrustScoreYearLinksFix
01LBDM
From paper: Large-scale spectral clustering using diffusion coordinates on landmark-based bipartite graphs
verified3.082018Paper ↗Looks wrong?
02U-SPEC
From paper: Ultra-Scalable Spectral Clustering and Ensemble Clustering
verified2.072021Paper ↗Code ↗Source ↗Looks wrong?
03SC_RB
From paper: Scalable Spectral Clustering Using Random Binning Features
verified1.802018Paper ↗Code ↗Looks wrong?
04LSC-K
From paper: Divide-and-conquer based Large-Scale Spectral Clustering
verified1.202021Paper ↗Code ↗Looks wrong?
05LSC-R
From paper: Divide-and-conquer based Large-Scale Spectral Clustering
verified0.772021Paper ↗Code ↗Looks wrong?
06DnC-SC
From paper: Divide-and-conquer based Large-Scale Spectral Clustering
verified0.642021Paper ↗Code ↗Looks wrong?
§ 04 · Submit a result

Add to the leaderboard.

← Back to Document OCR