General Knowledge Reasoning on MMLU-Pro (Sel-AUC, AUROC)
94.4Sel-AUCStructU+Self-ConsU
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| StructU+Self-ConsUModel=Claude 4.5 Sonnet, Aggregation=within2026.06 | 94.4 | 91.2 | |
| Self-ConsUModel=Qwen 3 32B2026.06 | 78.7 | 96.6 |
| Method | Links | ||
|---|---|---|---|
| StructU+Self-ConsUModel=Claude 4.5 Sonnet, Aggregation=within2026.06 | 94.4 | 91.2 | |
| Self-ConsUModel=Qwen 3 32B2026.06 | 78.7 | 96.6 |