Unified ranking
Compare foundation models in the TSC-FM Benchmark by accuracy, average rank and coverage, with Standard and Low-shot evaluation.
Only configurations covering all 198 unique datasets are eligible for the Standard Overall leaderboard.
Standard Overall Average Accuracy is the unweighted mean across 198 unique datasets. Every dataset receives equal weight. Other views use their displayed dataset coverage.
Standard and Low-shot specify the label budget; ICL and Frozen-Probe filter the Standard Overall results by prediction approach.
1 | GDUT · Huawei Noah’s Ark Lab · Université Paris Cité · MBZUAI · Shantou University | 78.56 |
2 | Huawei Noah’s Ark Lab · Université Paris Cité | 77.73 |
3 | SCUT · A*STAR · Khalifa University | 76.87 |
4 | Huawei Noah’s Ark Lab · Université Paris Cité | 76.62 |
5 | Auton Lab, Carnegie Mellon University | 76.23 |
6 | Inria · École Normale Supérieure–PSL | 76.10 |
7 | Auton Lab, Carnegie Mellon University | 75.35 |
8 | Inria · École Normale Supérieure–PSL | 73.83 |
9 | Auton Lab, Carnegie Mellon University | 72.01 |
10 | Microsoft Research · Peking University | 66.76 |
11 | Auton Lab, Carnegie Mellon University | 64.22 |
12 | Auton Lab, Carnegie Mellon University | 50.23 |
12 methods
Server-rendered result summary
These tables summarize the same verified results as the interactive explorer above and are included directly in the page HTML.
Protocol v0.1 · Release eb2c7961ff23
12 complete configurations across 198 datasets. Each dataset has equal weight; rank is ordered by mean accuracy and average rank is recomputed within this view.
| Rank | Configuration | Avg. Accuracy | Avg. Rank | Coverage |
|---|---|---|---|---|
| 1 | ChorusTIC | 78.56 | 3.94 | 198 / 198 |
| 2 | MantisV2+LR | 77.73 | 4.64 | 198 / 198 |
| 3 | UniShape+RF | 76.87 | 5.08 | 198 / 198 |
| 4 | MantisV2+RF | 76.62 | 5.42 | 198 / 198 |
| 5 | MOMENT+SVM | 76.23 | 5.22 | 198 / 198 |
18 complete configurations across 140 eligible datasets with five labeled examples per class. Results are ranked only against this budget and scope.
| Rank | Configuration | Avg. Accuracy | Avg. Rank | Coverage |
|---|---|---|---|---|
| 1 | MantisV2+ScaledLR | 66.33 | 7.21 | 140 / 140 |
| 2 | Mantis+ScaledLR | 66.32 | 7.15 | 140 / 140 |
| 3 | Mantis+LR | 66.32 | 7.24 | 140 / 140 |
| 4 | Mantis+SVM | 66.22 | 7.19 | 140 / 140 |
| 5 | ChorusTIC | 65.92 | 7.92 | 140 / 140 |
18 complete configurations across 121 eligible datasets with ten labeled examples per class. Results are ranked only against this budget and scope.
| Rank | Configuration | Avg. Accuracy | Avg. Rank | Coverage |
|---|---|---|---|---|
| 1 | Mantis+SVM | 72.07 | 6.60 | 121 / 121 |
| 2 | Mantis+ScaledLR | 71.82 | 6.71 | 121 / 121 |
| 3 | MantisV2+ScaledLR | 71.81 | 6.76 | 121 / 121 |
| 4 | ChorusTIC | 71.74 | 6.81 | 121 / 121 |
| 5 | Mantis+LR | 71.30 | 7.32 | 121 / 121 |
The two scopes use different dataset pools, so compare configurations within the same column rather than comparing their accuracy values as if they came from one test set.
How ranking works. Average Accuracy is the unweighted mean across the eligible datasets shown by Coverage. Exact accuracy ties within 1e-12 receive average ranks. Low-shot budgets and modality scopes remain separate.
Read the complete ranking rules and reproducibility protocol. The release identifier above is a content fingerprint for the currently published public results.
Start with Standard Overall to compare configurations covering all 198 datasets. Select Univariate or Multivariate when that matches your task. A model name can appear with several classifier heads: the head is part of the evaluated configuration, so the rankings compare complete prediction procedures.
For few-shot time series classification, select Low-shot and then 5-shot or 10-shot. Compare models within the same budget and scope; dataset eligibility changes with the label budget. Average accuracy weights each eligible dataset equally, while average rank describes performance relative to the comparison set.
The leaderboard reports classification, where a sequence is assigned a class label. It does not rank time series forecasting models on future-value prediction. Inspect the model pages for checkpoints and configuration results before selecting a model.
