| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Technical engineering calculation | TPS-CalcBench (test) | Delta KPI91.4 | 15 | |
| Mathematical reasoning and calculation | TPS-CalcBench (test) | KPI90.2 | 12 | |
| Outcome correctness | TPS-CalcBench core set v2 | Exact Match51.9 | 12 | |
| Engineering Problem Solving | TPS-CalcBench Track C | KPI87.85 | 12 |