AI Paper Atlas

Research map / Benchmarks / Text

Text leaderboard

14 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on Text. Best accuracy: 91.02 (Transformers + Rotary + Masked SPT, ICLR 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.

Text · accuracy

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

#accuracy ↑MethodPaperTopic
191.02Transformers + Rotary + Masked SPT
Transformer
Never Train from Scratch: Fair Comparison of Long-Sequence Models Requires Data-Driven Priors
ICLR 2024 · Table 2
Attention and transformers
289.4LRUResurrecting Recurrent Neural Networks for Long Sequences
ICML 2023 · Table 4
RNNs and normalization
388.32B₂S₆
Mamba S6
Block-Biased Mamba for Long-Range Sequence Processing
NeurIPS 2025 · Long-Range Arena table
Attention and transformers
486.82S4-LegSHow to Train your HIPPO: State Space Models with Generalized Orthogonal Basis Projections
ICLR 2023 · Long Range Arena results table
RNNs and normalization
583.32Paramixer (CDIL)Paramixer: Parameterizing Mixing Links in Sparse Factors Works Better Than Dot-Product Self-Attention
CVPR 2022 · Table 1
Attention and transformers
680.3ELM NeuronThe Expressive Leaky Memory Neuron: an Efficient and Expressive Phenomenological Neuron Model Can Solve Long-Horizon Tasks.
ICLR 2024 · Table 1
RNNs and normalization
779.28LaS
Transformer
Viewing Transformers Through the Lens of Long Convolutions Layers
ICML 2024 · Table 2
Attention and transformers
874.31MMLC-owfMixture of Experts Based Multi-Task Supervise Learning from Crowds
AAAI 2025 · Table: Accuracy of Learning-fr
Recognition and long-tail
968.4Transformer-LS (best)Long-Short Transformer: Efficient Transformers for Language and Vision
NeurIPS 2021 · Table 1
Attention and transformers
1065.89*YOSO-C-16
BERT-small
You Only Sample (Almost) Once: Linear Cost Self-Attention Via Bernoulli Sampling
ICML 2021 · Table (LRA test accuracy)
Attention and transformers
4 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.