Reasoning on 17 Reasoning Benchmarks Aggregate (test)
90.71AccuracyComplexHoT
Evaluation results
| Method | Links | |
|---|---|---|
| ComplexHoTModel=Star Model2025.03 | 90.71 | |
| HoT + SCModel=Star Model2025.03 | 90.39 | |
| HoTModel=Star Model2025.03 | 89.31 | |
| ComplexCoTModel=Star Model2025.03 | 89.11 | |
| HoT + SCModel=Mean2025.03 | 88.79 | |
| CoT + SCModel=Star Model2025.03 | 88.76 | |
| ComplexHoTModel=Mean2025.03 | 88.54 | |
| RQModel=Star Model2025.03 | 88.35 | |
| CoTModel=Star Model2025.03 | 87.61 | |
| HoTModel=Mean2025.03 | 87.24 | |
| HoT + SCModel=Lightning Model2025.03 | 87.18 | |
| ComplexCoTModel=Mean2025.03 | 86.45 | |
| ComplexHoTModel=Lightning Model2025.03 | 86.37 | |
| CoT + SCModel=Mean2025.03 | 86.22 | |
| RQModel=Mean2025.03 | 85.93 | |
| CoTModel=Mean2025.03 | 85.41 | |
| HoTModel=Lightning Model2025.03 | 85.17 | |
| ComplexCoTModel=Lightning Model2025.03 | 83.79 | |
| CoT + SCModel=Lightning Model2025.03 | 83.68 | |
| RQModel=Lightning Model2025.03 | 83.51 | |
| CoTModel=Lightning Model2025.03 | 83.21 |