| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Time-series Reasoning | TSRBench | Percept Score64.3 | 19 | |
| Scenario-based Reasoning (Overall) | TSRBench | Overall Accuracy86.55 | 15 | |
| Inferential Calculation | TSRBench | Accuracy77.14 | 15 | |
| Scenario Attribution | TSRBench | Accuracy87.5 | 15 | |
| Anomaly Detection | TSRBench | Accuracy91.67 | 15 |