List your company

Selective Prediction on HotpotQA

86.6Sel-AUCStructU+Self-ConsU (TrueSkill+PageRank)
70.06474.35778.6582.943Jun 15, 2026

Evaluation results

MethodLinks
StructU+Self-ConsU (TrueSkill+PageRank)Model=Amazon Nova Premier, Scope=within2026.0686.676.3
Self-ConsUModel=Claude 4.5 Sonnet2026.0683.965.6
StructU+Self-ConsU (TrueSkill+PageRank)Model=DeepSeek R1, Scope=within2026.0679.272.7
SemanticUModel=Qwen 3 32B2026.0670.761.2