List your company

Selective Prediction on Math-Synth

85.4Sel-AUCStructU+Self-ConsU (TrueSkill+PageRank)
38.91250.98163.0575.119Jun 15, 2026

Evaluation results

MethodLinks
StructU+Self-ConsU (TrueSkill+PageRank)Model=GPT-OSS 20B, Scope=within2026.0685.496.1
StructU+Self-ConsU (TrueSkill+PageRank)Model=DeepSeek R1, Scope=within2026.0682.392.4
StructU+Self-ConsU (TrueSkill+PageRank)Model=Claude 4.5 Sonnet, Scope=across2026.0666.199.1
StructU+Self-ConsU (TrueSkill+PageRank)Model=Claude 4.5 Sonnet, Scope=within2026.066699.2
StructU+Self-ConsU (TrueSkill+PageRank)Model=Claude 4.5 Sonnet, Scope=total2026.066699.2
Self-ConsUModel=Claude 4.5 Sonnet2026.066598.5
StructU (TrueSkill+PageRank)Model=Claude 4.5 Sonnet, Scope=across2026.0664.195.8
StructU (TrueSkill+PageRank)Model=Claude 4.5 Sonnet, Scope=within2026.0662.797.8
StructU (TrueSkill+PageRank)Model=Claude 4.5 Sonnet, Scope=total2026.065894
VerbalizedUModel=Claude 4.5 Sonnet2026.0654.492.4
StructU+Self-ConsU (TrueSkill+PageRank)Model=Amazon Nova Premier, Scope=total2026.0650.499.8
SemanticUModel=Claude 4.5 Sonnet2026.064392.7
StructU+Self-ConsU (TrueSkill+PageRank)Model=Qwen 3 32B, Scope=within2026.0640.799.6