| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Code Reasoning | OJBench | Accuracy10.34 | 24 | |
| Code Generation | OJBench ICPC 2025 (test) | Accuracy19.18 | 18 | |
| Competitive Coding | OJBench | Best@8 Score45.9 | 16 | |
| Coding | OJBench | Accuracy40.7 | 12 | |
| Code Generation | OJBench | Accuracy58.8 | 10 | |
| Algorithmic Correctness Evaluation | OJBench | Overall Score71.5 | 3 |