Language Modelling on LRA
Metric: Avg (higher is better)
Metric: Avg (higher is better)
| # | Model↕ | Avg▼ | Extra Data | Paper | Date↕ | Code |
|---|---|---|---|---|---|---|
| 1 | S5 | 87.46 | No | Simplified State Space Layers for Sequence Model... | 2022-08-09 | Code |
| 2 | S4 | 86.09 | No | How to Train Your HiPPO: State Space Models with... | 2022-06-24 | Code |
| 3 | Converter | 75.94 | No | Converting Transformers into DGNNs Form | 2025-02-01 | Code |
| 4 | Transformer | 54.39 | No | Long Range Arena: A Benchmark for Efficient Tran... | 2020-11-08 | Code |
| 5 | Performer | 51.41 | No | Long Range Arena: A Benchmark for Efficient Tran... | 2020-11-08 | Code |
| 6 | Sparse Trans. | 51.24 | No | Long Range Arena: A Benchmark for Efficient Tran... | 2020-11-08 | Code |
| 7 | Linear Trans. | 50.55 | No | Long Range Arena: A Benchmark for Efficient Tran... | 2020-11-08 | Code |