# Fine-grained Sentiment Classification on SST-5 (test) Source: [Fine-grained Sentiment Classification on SST-5 (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:34:16.056Z Evaluation of fine-grained sentiment classification performance on the test split of the Stanford Sentiment Treebank (SST-5), measured by error rate. A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. | Scope | Recorded value | | --- | --- | | Task | Fine-grained Sentiment Classification | | Dataset (including any stated split) | Stanford Sentiment Treebank (SST) (test) | | Metric | Accuracy (Fine-grained) | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 25 of 25 | | Coverage | All results currently returned for this benchmark | Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol. ## Metrics - [Accuracy (Fine-grained)](): Higher is better; unit: PERCENT. - [Error Rate (Fine-grained)](): Lower is better; unit: PERCENT. ## Recorded results | Method | Accuracy (Fine-grained) | Result date | Report paper | | --- | --- | --- | --- | | CNN-RNF-LSTM | 53.4 | Not recorded | 68fa64bd1e209131cea06304 | | Lei et al., 2017 | 53.2 | Not recorded | 68fa64bd1e209131cea06304 | | CNN-RNF-GRU | 53 | Not recorded | 68fa64bd1e209131cea06304 | | NSE | 52.8 | Not recorded | 68fa63051e209131ce9fc644 | | DMN | 52.1 | Not recorded | 68fa63051e209131ce9fc644 | | GRU-maxpool | 51.7 | Not recorded | 68fa64bd1e209131cea06304 | | LSTM-maxpool | 51.6 | Not recorded | 68fa64bd1e209131cea06304 | | CT-LSTM | 51 | Not recorded | 68fa63051e209131ce9fc644 | | GRU | 50.5 | Not recorded | 68fa64bd1e209131cea06304 | | LSTM | 50.3 | Not recorded | 68fa64bd1e209131cea06304 | | DRNN | 49.8 | Not recorded | 68fa63051e209131ce9fc644 | | Bi-LSTM | 49.1 | Not recorded | 68fa63051e209131ce9fc644 | | Paragraph Vector | 48.7 | Not recorded | 68fa63051e209131ce9fc644 | | CNN-linear-filter | 48 | Not recorded | 68fa64bd1e209131cea06304 | | CNN-MC | 47.4 | Not recorded | 68fa63051e209131ce9fc644 | | 2-layer LSTM | 46 | Not recorded | 68fa63051e209131ce9fc644 | | RNTN | 45.7 | Not recorded | 68fa63051e209131ce9fc644 | ### CNN-RNF-LSTM Accuracy (Fine-grained): 53.4. Result ID: 698c89cb0b614d12cff17016. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Category":"CNN variants","Word Vectors":"GloVe 300d"}. This record does not assert independent reproduction. ### Lei et al., 2017 Accuracy (Fine-grained): 53.2. Result ID: 698c89cb0b614d12cff1701b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Description":"Best published results"}. This record does not assert independent reproduction. ### CNN-RNF-GRU Accuracy (Fine-grained): 53. Result ID: 698c89cb0b614d12cff17015. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Category":"CNN variants","Word Vectors":"GloVe 300d"}. This record does not assert independent reproduction. ### NSE Accuracy (Fine-grained): 52.8. Result ID: 698c6e4837894ef7d9ce54e7. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"word embeddings":"300-D Glove 840B"}. This record does not assert independent reproduction. ### DMN Accuracy (Fine-grained): 52.1. Result ID: 698c6e4837894ef7d9ce54e6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### GRU-maxpool Accuracy (Fine-grained): 51.7. Result ID: 698c89cb0b614d12cff17019. [Reporting paper]() Recorded evaluation configuration: {"Category":"RNN variants","Word Vectors":"GloVe 300d"}. This record does not assert independent reproduction. ### LSTM-maxpool Accuracy (Fine-grained): 51.6. Result ID: 698c89cb0b614d12cff1701a. [Reporting paper]() Recorded evaluation configuration: {"Category":"RNN variants","Word Vectors":"GloVe 300d"}. This record does not assert independent reproduction. ### CT-LSTM Accuracy (Fine-grained): 51. Result ID: 698c6e4837894ef7d9ce54e5. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### GRU Accuracy (Fine-grained): 50.5. Result ID: 698c89cb0b614d12cff17017. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"RNN variants","Word Vectors":"GloVe 300d"}. This record does not assert independent reproduction. ### LSTM Accuracy (Fine-grained): 50.3. Result ID: 698c89cb0b614d12cff17018. [Reporting paper]() Recorded evaluation configuration: {"Category":"RNN variants","Word Vectors":"GloVe 300d"}. This record does not assert independent reproduction. ### DRNN Accuracy (Fine-grained): 49.8. Result ID: 698c6e4837894ef7d9ce54e2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Bi-LSTM Accuracy (Fine-grained): 49.1. Result ID: 698c6e4837894ef7d9ce54e4. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"bidirectional":"true"}. This record does not assert independent reproduction. ### Paragraph Vector Accuracy (Fine-grained): 48.7. Result ID: 698c6e4837894ef7d9ce54e0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### CNN-linear-filter Accuracy (Fine-grained): 48. Result ID: 698c89cb0b614d12cff17014. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Category":"CNN variants","Word Vectors":"GloVe 300d"}. This record does not assert independent reproduction. ### CNN-MC Accuracy (Fine-grained): 47.4. Result ID: 698c6e4837894ef7d9ce54e1. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### 2-layer LSTM Accuracy (Fine-grained): 46. Result ID: 698c6e4837894ef7d9ce54e3. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"layers":"2"}. This record does not assert independent reproduction. ### RNTN Accuracy (Fine-grained): 45.7. Result ID: 698c6e4837894ef7d9ce54df. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.