AI Paper Atlas

Research map / Benchmarks / IMDB

IMDB leaderboard

129 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on IMDB. Best accuracy: 97.28 (Vector-ICL (finetuned), ICLR 2025).

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.

IMDB · accuracy

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

#accuracy ↑MethodPaperTopic
197.28Vector-ICL (finetuned)
Llama-3.1-8B; NV-Embed-v1
Vector-ICL: In-context Learning with Continuous Vector Representations
ICLR 2025 · Table: sentiment analysis and
Language, safety and interpretability
296.8LS-large
RoBERTa-large
Long-Short Transformer: Efficient Transformers for Language and Vision
NeurIPS 2021 · IMDb results table
Attention and transformers
396.72Transformer w/ MI estimation
BERT_base
Faster Depth-Adaptive Transformers
AAAI 2021 · Main results table
Attention and transformers
496.6Mask Matching
RoBERTa-large
Labels Need Prompts Too: Mask Matching for Natural Language Understanding Tasks
AAAI 2024 · Full-training results table
Language, safety and interpretability
595.96Ours
BERT-Large
On the Generalization Effects of Linear Transformations in Data Augmentation
ICML 2020 · text
Recognition and long-tail
695.95GLOT
Mistral-7B (frozen)
Towards Improved Sentence Representations using Token Graphs
ICLR 2026 · Table 2
Graph self-supervised learning
795.8BERT+Gater
BERT
Reducing Sentiment Bias in Pre-trained Sentiment Classification via Adaptive Gumbel Attack
AAAI 2023 · Table 2
Recognition and long-tail
895.7TA-VAT
BERT
Token-Aware Virtual Adversarial Training in Natural Language Understanding
AAAI 2021 · Table 4
Attacks on text and graphs
994.8KCReg (ours)
BERT
Achieving Domain-Independent Certified Robustness via Knowledge Continuity
NeurIPS 2024 · Table 1
Domain adaptation and generalization
1094.7Ours (F_sum)
RoBERTa
Model Merging by Uncertainty-Based Gradient Matching
ICLR 2024 · Table: Sentiment Classificatio
RNNs and normalization
84 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

IMDB · F1

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

3 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

IMDB · macro-F1

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

2 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

IMDB · error rate

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

#error rate ↓MethodPaperTopic
14.4MPNet
BERT base
MPNet: Masked and Permuted Pre-training for Language Understanding
NeurIPS 2020 · RACE and IMDB results table
Language, safety and interpretability
25.5Description (Ext.)
BERT
Description Based Text Classification with Reinforcement Learning
ICML 2020 · Table 1
Recognition and long-tail
35.94o-2LSTM-p + CNN tv-embeddings
o-2LSTM-p + LSTM tv-embeddings
Supervised and Semi-Supervised Text Categorization using LSTM for Region Embeddings
ICML 2016 · Combining tv-embeddings table
Semi-supervised learning
46.005Adversarial dropout on recurrent connection (K=2)
LSTM
Adversarial Dropout for Recurrent Neural Networks
AAAI 2019 · Table 2
RNNs and normalization
56.07ADV-LM-LSTM + IMN
ADV-LM-LSTM
Mixture of Expert/Imitator Networks: Scalable Semi-Supervised Learning Framework
AAAI 2019 · Results table
Semi-supervised learning
67.5MergeNet
DistilBERT
MergeNet: Knowledge Migration Across Heterogeneous Models, Tasks, and Modalities
AAAI 2025 · Cross-task results table
Knowledge distillation
79.2sr-LSTM-p (k=10, best variant)State-Regularized Recurrent Neural Networks to Extract Automata and Explain Predictions
TPAMI 2022 · Table 4
RNNs and normalization
810.51SVM-DSNSVM-Based Deep Stacking Networks
AAAI 2019 · IMDB Classification Performanc
RNNs and normalization
911.93FC-B NFT
FC-B
Being Friends Instead of Adversaries: Deep Networks Learn from Data Simplified by Other Networks
AAAI 2022 · Table (Sentiment Analysis)
Certified and empirical robustness
1013.4RCN+A (RF ruleset)
Bi-LSTM
Deep Neural Networks Constrained by Decision Rules
AAAI 2019 · Table 3
Prediction and decision losses
2 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

IMDB · micro-F1

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

1 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

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