# mTSBench: Benchmarking Multivariate Time Series Anomaly Detection and Model Selection at Scale

arXiv: https://arxiv.org/abs/2506.21550 · HTML: https://mlsanity.com/paper/2506.21550/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 43 of its 103 references that are in the map.
- First posted on arXiv 26 Jun 2025.

## Builds on (most cited first, 30 of 43)

- [TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysis](https://mlsanity.com/paper/2210.02186/) (2022)
- [One Fits All:Power General Time Series Analysis by Pretrained LM](https://mlsanity.com/paper/2302.11939/) (2023)
- [Transformers in Time Series: A Survey](https://mlsanity.com/paper/2202.07125/) (2022)
- [Detecting Spacecraft Anomalies Using LSTMs and Nonparametric Dynamic Thresholding](https://mlsanity.com/paper/1802.04431/) (2018)
- [Anomaly Transformer: Time Series Anomaly Detection with Association Discrepancy](https://mlsanity.com/paper/2110.02642/) (2021)
- [Deep Learning for Anomaly Detection: A Survey](https://mlsanity.com/paper/1901.03407/) (2019)
- [Time-Series Representation Learning via Temporal and Contextual Contrasting](https://mlsanity.com/paper/2106.14112/) (2021)
- [Unsupervised Anomaly Detection via Variational Auto-Encoder for Seasonal KPIs in Web Applications](https://mlsanity.com/paper/1802.03903/) (2018)
- [TranAD: Deep Transformer Networks for Anomaly Detection in Multivariate Time Series Data](https://mlsanity.com/paper/2201.07284/) (2022)
- [FITS: Modeling Time Series with 10k Parameters](https://mlsanity.com/paper/2307.03756/) (2023)
- [A review on outlier/anomaly detection in time series data](https://mlsanity.com/paper/2002.04236/) (2020)
- [Current Time Series Anomaly Detection Benchmarks are Flawed and are Creating the Illusion of Progress](https://mlsanity.com/paper/2009.13807/) (2020)
- [COPOD: Copula-Based Outlier Detection](https://mlsanity.com/paper/2009.09463/) (2020)
- [A Survey on Graph Neural Networks for Time Series: Forecasting, Classification, Imputation, and Anomaly Detection](https://mlsanity.com/paper/2307.03759/) (2023)
- [Deep Learning for Time Series Anomaly Detection: A Survey](https://mlsanity.com/paper/2211.05244/) (2022)
- [Evaluating Real-time Anomaly Detection Algorithms - the Numenta Anomaly Benchmark](https://mlsanity.com/paper/1510.03336/) (2015)
- [Extended Isolation Forest](https://mlsanity.com/paper/1811.02141/) (2018)
- [Local Evaluation of Time Series Anomaly Detection Algorithms](https://mlsanity.com/paper/2206.13167/) (2022)
- [An Evaluation of Anomaly Detection and Diagnosis in Multivariate Time Series](https://mlsanity.com/paper/2109.11428/) (2021)
- [Precision and Recall for Time Series](https://mlsanity.com/paper/1803.03639/) (2018)
- [Anomaly Detection in Univariate Time-series: A Survey on the State-of-the-Art](https://mlsanity.com/paper/2004.00433/) (2020)
- [Exathlon: A Benchmark for Explainable Anomaly Detection over Time Series](https://mlsanity.com/paper/2010.05073/) (2020)
- [Large Language Models for Forecasting and Anomaly Detection: A Systematic Literature Review](https://mlsanity.com/paper/2402.10350/) (2024)
- [Position: What Can Large Language Models Tell Us about Time Series Analysis](https://mlsanity.com/paper/2402.02713/) (2024)
- [A Survey on Explainable Anomaly Detection](https://mlsanity.com/paper/2210.06959/) (2022)
- [Multivariate Industrial Time Series with Cyber-Attack Simulation: Fault Detection Using an LSTM-based Predictive Data Model](https://mlsanity.com/paper/1612.06676/) (2016)
- [Probabilistic Matrix Factorization for Automated Machine Learning](https://mlsanity.com/paper/1705.05355/) (2017)
- [Universal Time-Series Representation Learning: A Survey](https://mlsanity.com/paper/2401.03717/) (2024)
- [Automatic Anomaly Detection in the Cloud Via Statistical Learning](https://mlsanity.com/paper/1704.07706/) (2017)
- [Unsupervised Model Selection for Time-series Anomaly Detection](https://mlsanity.com/paper/2210.01078/) (2022)

## Built on by (most cited first, 7 of 7)

- [Anomalies in Multivariate Time Series Benchmarks Are Mostly Univariate](https://mlsanity.com/paper/2606.02670/) (2026)
- [LLM-Assisted Logic Rule Learning: Scaling Human Expertise for Time Series Anomaly Detection](https://mlsanity.com/paper/2601.19255/) (2026)
- [Budgeted Indirect Adversarial Attack on Graph-Based Anomaly Detection in Sensor Networks](https://mlsanity.com/paper/2509.17987/) (2025)
- [Tiny but Trusted: Efficient Vision-Language Reasoning for Time-Series Anomaly Detection](https://mlsanity.com/paper/2605.30344/) (2026)
- [CRAFTIIF: Cross-Resolution Analytic Four-Type Interpretable Isolation Forest for Multivariate Time Series Anomaly Detection](https://mlsanity.com/paper/2606.13486/) (2026)
- [Graph-Spectral Flow Matching for Multivariate Time Series Anomaly Detection](https://mlsanity.com/paper/2609.36765/) (2026)
- [OneShot: Label-Efficient Detector Weighting for Time Series Anomaly Detection](https://mlsanity.com/paper/2610.16219/) (2026)

## Abstract (arXiv)

Anomaly detection in multivariate time series is essential across domains such as healthcare, cybersecurity, and industrial monitoring, yet remains fundamentally challenging due to high-dimensional dependencies, the presence of cross-correlations between time-dependent variables, and the scarcity of labeled anomalies. We introduce mTSBench, the largest benchmark to date for multivariate time series anomaly detection and model selection, consisting of 344 labeled time series across 19 datasets from a wide range of application domains. We comprehensively evaluate 24 anomaly detectors, including the only two publicly available large language model-based methods for multivariate time series. Consistent with prior findings, we observe that no single detector dominates across datasets, motivating the need for effective model selection. We benchmark three recent model selection methods and find that even the strongest of them remain far from optimal. Our results highlight the outstanding need for robust, generalizable selection strategies. We open-source the benchmark at https://plan-lab.github.io/mtsbench to encourage future research.