Mathematical Reasoning on AIME-25 (Sel-AUC, AUROC)
0.886Sel-AUCStructU+Self-ConsU
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| StructU+Self-ConsUModel=GPT-OSS 20B, Aggregation=total2026.06 | 0.886 | 1 | |
| StructUModel=DeepSeek R1, Aggregation=total2026.06 | 0.539 | 0.466 |
Loading the SOTA2 catalog…