Selective Prediction on AIME-25
0.886Sel-AUCStructU+Self-ConsU (TrueSkill+PageRank)
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| StructU+Self-ConsU (TrueSkill+PageRank)Model=GPT-OSS 20B, Scope=total2026.06 | 0.886 | 1 | |
| StructU+Self-ConsU (TrueSkill+PageRank)Model=DeepSeek R1, Scope=total2026.06 | 0.754 | 1 | |
| StructU+Self-ConsU (TrueSkill+PageRank)Model=Claude 4.5 Sonnet, Scope=total2026.06 | 0.646 | 1 | |
| StructU+Self-ConsU (TrueSkill+PageRank)Model=Qwen 3 32B, Scope=total2026.06 | 0.313 | 1 |