AI Paper Atlas

Research map / Benchmarks / SST

SST leaderboard

23 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on SST. Best accuracy: 96.6 (Switchable Decision, ICML 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.

SST · accuracy

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

#accuracy ↑MethodPaperTopic
196.6Switchable Decision
BART-large
Switchable Decision: Dynamic Neural Generation Networks
ICML 2024 · Table: Performance on GLUE
RNNs and normalization
295.7GPT-J-6B AMA
GPT-J-6B
Ask Me Anything: A simple strategy for prompting language models
ICLR 2023 · Table 1
Language, safety and interpretability
393.81UNIREX (DLM-FP)
BigBird-Base
UNIREX: A Unified Learning Framework for Language Model Rationale Extraction
ICML 2022 · Computational Efficiency Resul
Language, safety and interpretability
492.98InterpretCC Top K Routing
DistilBERT
Intrinsic User-Centric Interpretability through Global Mixture of Experts
ICLR 2025 · Table, InterpretCC Performance
Recognition and long-tail
592.1CoTACS k=3, 13B, 1000 examples
Llama-2 13B
Learning to Reason via Program Generation, Emulation, and Search
NeurIPS 2024 · main results table
Agents, code and math
688.94bBeta-LSTM(5G+p)Bivariate Beta-LSTM
AAAI 2020 · Table 1
RNNs and normalization
788.4GloVe LSTM+C
LSTM with GloVe
Counterfactual Vision and Language Learning
CVPR 2020 · Table 1
Visual question answering
888.19UST
BERT-Base
Uncertainty-aware Self-training for Few-shot Text Classification
NeurIPS 2020 · Table 2
Semi-supervised learning
986.4CNN-Complex-order
CNN
Encoding word order in complex embeddings
ICLR 2020 · Text classification results ta
RNNs and normalization
1086.4Skim-LSTM
LSTM
Neural Speed Reading via Skim-RNN
ICLR 2018 · Text classification results ta
RNNs and normalization
13 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.