M4
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Short-term forecasting | M4 Quarterly | MASE0.062 | 141 | |
| Short-term forecasting | M4 Monthly | MASE0.709 | 125 | |
| Short-term forecasting | M4 Yearly | MASE0.091 | 116 | |
| Short-term forecasting | M4 (Others) | SMAPE3.789 | 83 | |
| Short-term forecasting | M4 | SMAPE4.633 | 74 | |
| Short-term time series forecasting | M4 Average | SMAPE11.73 | 53 | |
| Short-term forecasting | M4 (test) | SMAPE11.701 | 35 | |
| Short-term forecasting | M4 Weighted Average | SMAPE11.618 | 32 | |
| Machine-Generated Text Detection | M4 | TP @ 20%87.28 | 32 | |
| Time Series Forecasting | M4 Daily | MASE2.054 | 31 | |
| Short-term time series forecasting | M4 weighted average from all datasets (test) | sMAPE11.829 | 30 | |
| Time Series Forecasting | M4 Weekly | MASE0.354 | 17 | |
| Multi-contrast MRI Reconstruction | M4raw | PSNR (dB)32.01 | 16 | |
| AI-generated text detection | M4 | AUROC92.43 | 13 | |
| Forecasting | M4 hourly 48 | Relative MAPE0.54 | 13 | |
| Forecasting | M4 | CRPS0.036 | 13 | |
| Time Series Forecasting | M4 Hourly | SMAPE10.84 | 12 | |
| Time Series Forecasting | m4 Chronos Benchmark II (yearly) | WQL0.091 | 12 | |
| Time Series Forecasting | m4 Chronos Benchmark II (quarterly) | WQL0.062 | 12 | |
| Time-series Forecasting | M4 (test) | CRPS0.03 | 12 | |
| Time-series Forecasting | M4 Zero-shot | Yearly sMAPE13.53 | 10 | |
| Time Series Forecasting | M4 Others | sMAPE6.245 | 10 | |
| Univariate Time Series Forecasting | M4 | SMAPE11.863 | 10 | |
| Detection of LLM-generated text | M4 extension Generation: Polish 4o-mini, Regeneration: Para 4o-mini | ROC AUC @ 1% FPR0.1329 | 8 | |
| Detection of LLM-generated text | M4 extension Generation Revise 4.1 Regeneration Para 4o-mini | ROC AUC @ 1% FPR25.26 | 8 |
Showing 25 of 58 rows