Metric: MAE (lower is better)
| # | Model↕ | MAE▲ | Extra Data | Paper | Date↕ | Code |
|---|---|---|---|---|---|---|
| 1 | xPatch | 0.297 | No | xPatch: Dual-Stream Time Series Forecasting with... | 2024-12-23 | Code |
| 2 | PatchMixer | 0.3 | No | PatchMixer: A Patch-Mixing Architecture for Long... | 2023-10-01 | Code |
| 3 | SegRNN | 0.32 | No | SegRNN: Segment Recurrent Neural Network for Lon... | 2023-08-22 | Code |
| 4 | LTBoost (drop_last=false) | 0.329 | No | - | - | Code |
| 5 | RLinear | 0.331 | No | Revisiting Long-term Time Series Forecasting: An... | 2023-05-18 | Code |
| 6 | TiDE | 0.336 | No | Long-term Forecasting with TiDE: Time-series Den... | 2023-04-17 | Code |
| 7 | PatchTST/64 | 0.337 | No | A Time Series is Worth 64 Words: Long-term Forec... | 2022-11-27 | Code |
| 8 | TSMixer | 0.337 | No | TSMixer: Lightweight MLP-Mixer Model for Multiva... | 2023-06-14 | Code |
| 9 | TEFN | 0.337 | No | Time Evidence Fusion Network: Multi-source View ... | 2024-05-10 | Code |
| 10 | NLinear | 0.338 | No | Are Transformers Effective for Time Series Forec... | 2022-05-26 | Code |
| 11 | FiLM | 0.348 | No | FiLM: Frequency improved Legendre Memory Model f... | 2022-05-18 | Code |
| 12 | DLinear | 0.353 | No | Are Transformers Effective for Time Series Forec... | 2022-05-26 | Code |