Codesota · Benchmark · CoraHome/Leaderboards/Structured Data & Forecasting/Node Classification/Cora
Unknown

Cora.

Citation network of scientific papers. 2708 nodes, 5429 edges, 7 classes. Classic GNN benchmark.

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 ↗

accuracy

Accuracy is the reported evaluation metric for Cora. 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

Muted rows were not state of the art when published — an earlier or same-year result already scored better.

RankModelTrustScoreYearLinksFix
01TAPE + RevGAT
TAPE (LLM-to-LM Interpreter) + RevGAT backbone. ICLR 2024. He et al. Uses LLM-generated explanations as node features. Supervised split.
verified92.92024Source ↗Looks wrong?
02AuGLM (T5-large)
AuGLM with T5-large backbone. Text-output node classifier. Xu et al. 2024 "How to Make LMs Strong Node Classifiers?" Table 1.
verified91.512024Source ↗Looks wrong?
03ENGINE
ENGINE vector-output model. Result from AuGLM comparison table (Table 1) in Xu et al. 2024.
verified91.482024Source ↗Looks wrong?
04InstructGLM
InstructGLM text-output model. Result from AuGLM comparison table (Table 1) in Xu et al. 2024.
verified90.772024Source ↗Looks wrong?
05GLEM + RevGAT
GLEM (Graph-LM EM framework) + RevGAT backbone. From AuGLM comparison table (Table 1) in Xu et al. 2024.
verified88.562024Source ↗Looks wrong?
06GCNLLMEmb
GCN with LLM-generated embeddings, supervised setting. From comprehensive LLM-based node classification analysis, Feb 2025.
verified88.152025Source ↗Looks wrong?
07LLaGA (Mistral-7B)
LLaGA with Mistral-7B backbone, supervised setting. Xu et al. 2024 Table 6.
verified87.552024Source ↗Looks wrong?
08SDGAT
Sparse graphs-based Dynamic Attention Network. ~3% improvement over baselines on Cora. Published PMC Dec 2024.
verified85.292024Source ↗Looks wrong?
09GCN* (tuned)
GCN with proper hyperparameter tuning. Best model in NeurIPS 2024 "Classic GNNs are Strong Baselines" (Table 2). Luo et al.
verified85.082024Source ↗Looks wrong?
10GAT* (tuned)
GAT with proper hyperparameter tuning. NeurIPS 2024 "Classic GNNs are Strong Baselines" (Table 2).
verified84.642024Source ↗Looks wrong?
11SGFormer
SGFormer result from NeurIPS 2024 "Classic GNNs are Strong Baselines" (Table 2). Wu et al.
verified84.52024Source ↗Looks wrong?
12GraphSAGE* (tuned)
GraphSAGE with proper hyperparameter tuning. NeurIPS 2024 "Classic GNNs are Strong Baselines" (Table 2).
verified84.182024Source ↗Looks wrong?
13ACNet
From paper: Adaptively Connected Neural Networks
verified83.52019Paper ↗Code ↗Looks wrong?
14LGCN
From paper: Large-Scale Learnable Graph Convolutional Networks
verified83.32018Paper ↗Code ↗Looks wrong?
15Polynormer
Polynormer result from NeurIPS 2024 "Classic GNNs are Strong Baselines" (Table 2).
verified83.252024Source ↗Looks wrong?
16GOAT
GOAT (Graph Transformer) result from NeurIPS 2024 "Classic GNNs are Strong Baselines" (Table 2).
verified83.182024Source ↗Looks wrong?
17GAT
Graph Attention Network. Velickovic et al., ICLR 2018.
verified832018Source ↗Looks wrong?
18GraphGPS
GraphGPS result from NeurIPS 2024 "Classic GNNs are Strong Baselines" (Table 2). Rampasek et al. original model.
verified82.842024Source ↗Looks wrong?
19Exphormer
Exphormer result from NeurIPS 2024 "Classic GNNs are Strong Baselines" (Table 2).
verified82.772024Source ↗Looks wrong?
20GraphSAGE
GraphSAGE result from NeurIPS 2024 "Classic GNNs are Strong Baselines" paper (Table 2). Luo et al.
verified82.682024Source ↗Looks wrong?
21NodeFormer
NodeFormer result from NeurIPS 2024 "Classic GNNs are Strong Baselines" (Table 2).
verified82.22024Source ↗Looks wrong?
22NAGphormer
NAGphormer result from NeurIPS 2024 "Classic GNNs are Strong Baselines" (Table 2).
verified82.122024Source ↗Looks wrong?
23MoNet
From paper: Geometric deep learning on graphs and manifolds using mixture model CNNs
verified81.72016Paper ↗Code ↗Looks wrong?
24GCN
Graph Convolutional Network. Kipf & Welling, ICLR 2017. Standard semi-supervised split.
verified81.52017Source ↗Looks wrong?
25Planetoid*
From paper: Revisiting Semi-Supervised Learning with Graph Embeddings
verified75.72016Paper ↗Code ↗Looks wrong?
26DeepWalk
From paper: DeepWalk: Online Learning of Social Representations
verified67.22014Paper ↗Code ↗Looks wrong?
§ 04 · Submit a result

Add to the leaderboard.

← Back to Node Classification
Cora Leaderboard | CodeSOTA | CodeSOTA