Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Mathematical Reasoning on AMC 23 (Sel-AUC, AUROC)
Loading...
0.985
Sel-AUC
StructU+Self-ConsU
0.70732
0.77941
0.8515
0.92359
Jun 15, 2026
Sel-AUC
AUROC
Updated 1mo ago
Evaluation Results
Method
Method
Links
Sel-AUC
AUROC
StructU+Self-ConsU
Model=DeepSeek R1, Agg...
2026.06
0.985
1
StructU
Model=Claude 4.5 Sonne...
2026.06
0.967
1
Self-ConsU
Model=Claude 4.5 Sonnet
2026.06
0.955
1
Self-ConsU
Model=Qwen 3 32B
2026.06
0.81
1
StructU+Self-ConsU
Model=Amazon Nova Prem...
2026.06
0.718
1
Feedback
Search any
task
Search any
task