| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Math Reasoning | Gaokao En 2023 | Accuracy79 | 91 | |
| Mathematical Reasoning | GaoKao (test) | Accuracy79.74 | 61 | |
| Mathematical Problem Solving | Gaokao MathQA | Accuracy86.3 | 60 | |
| Mathematical Reasoning | Gaokao | Accuracy80 | 51 | |
| Mathematical Reasoning | GaoKao En 2023 | Pass@1 Accuracy79.7 | 39 | |
| Knowledge Intensive | Gaokao History | Accuracy83 | 30 | |
| Comprehensive Examination | GAOKAO (test) | Accuracy76.3 | 27 | |
| Mathematical Reasoning | Gaokao 2023 | Accuracy@12847.7 | 21 | |
| Knowledge Intensive | Gaokao Geography | Accuracy79.8 | 20 | |
| Mathematical Reasoning | GAOKAO-en | Pass Rate73 | 20 | |
| Mathematical Reasoning | Gaokao | Average Score (@16)87.11 | 19 | |
| Mathematical Reasoning | Gaokao | Pass@135.4 | 18 | |
| Mathematical Reasoning | Gaokao En 23 | Accuracy78.4 | 18 | |
| Mathematical Problem Solving | Gaokao MathCloze | Accuracy72.9 | 18 | |
| Mathematical Reasoning | Gaokao MathCloze | Pass@169.5 | 10 | |
| Mathematical Reasoning | Gaokao Mix 2024 | Pass@135.2 | 10 | |
| Mathematical Reasoning | Gaokao I 2024 | Pass@142.9 | 10 | |
| Examination | Gaokao | Accuracy82.8 | 10 | |
| Autoformalization | Gaokao Formal | Mean Score74.2 | 8 | |
| Mathematical formalization | Gaokao-Formal 495 problems | Correctness @184.2 | 8 | |
| Precise Length Constraint | GAOKAO-History Chinese Dataset | E Score27.41 | 2 |