AI Paper Atlas

Research map / Benchmarks / Criteo

Criteo leaderboard

16 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on Criteo. Best AUC: 0.8477 (MISS, AAAI 2024).

Numbers are as each paper reports them, read by AI from its results tables and not checked by hand. Papers can differ in setting (training data, model size, extra data); the topic column shows what each paper is about. Open the paper before you compare or quote a number.

Criteo · AUC

16 papers, each with its best reported number for its own method; higher is better.

#AUC ↑MethodPaperTopic
10.8477MISS
DNN
Online Conversion Rate Prediction via Multi-Interval Screening and Synthesizing under Delayed Feedback
AAAI 2024 · Table 3
Recognition and long-tail
20.8165REACTIONREACTION: Parameter-Efficient Learning for Recommendation
AAAI 2026 · Table 1
Recognition and long-tail
30.8148FinalMLPFinalMLP: An Enhanced Two-Stream MLP Model for CTR Prediction
AAAI 2023 · Table: Bilinear fusion with di
Recognition and long-tail
40.8147DCN V2 GEN
DCN V2
From Feature Interaction to Feature Generation: A Generative Paradigm of CTR Prediction Models
ICML 2025 · Table 1
Recognition and long-tail
50.8145MDLExploiting Field Dependencies for Learning on Categorical Data
TPAMI 2023 · Table 2
Matrix and tensor methods
60.8144ALPT(SR)
DCN
Adaptive Low-Precision Training for Embeddings in Click-Through Rate Prediction
AAAI 2023 · Table 1
Quantization
70.8138DCNv2 ME 10x
DCNv2
On the Embedding Collapse when Scaling up Recommendation Models
ICML 2024 · Table: Results on Criteo datas
Recognition and long-tail
80.8129Field-wise LearningField-wise Learning for Multi-field Categorical Data
NeurIPS 2020 · Experiment results table
Kernels and regression theory
90.8116OptFeatureTowards Hybrid-grained Feature Interaction Selection for Deep Sparse Network
NeurIPS 2023 · Table 1
Attention and transformers
100.8097DeepFM + GLIDER
DeepFM
Feature Interaction Interpretability: A Case for Explaining Ad-Recommendation Systems via Neural Interaction Detection
ICLR 2020 · Table: Test prediction perform
Recognition and long-tail
6 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

Criteo · Logloss

10 papers, each with its best reported number for its own method; lower is better.

Not affiliated with any conference, journal or the benchmark's authors. Corrections: contact@latenticlabs.com.