List your company

General Knowledge Reasoning on MMLU-Pro (Sel-AUC, AUROC)

94.4Sel-AUCStructU+Self-ConsU
78.07282.31186.5590.789Jun 15, 2026

Evaluation results

MethodLinks
StructU+Self-ConsUModel=Claude 4.5 Sonnet, Aggregation=within2026.0694.491.2
Self-ConsUModel=Qwen 3 32B2026.0678.796.6