Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Selective Prediction on AIME 24
Loading...
92.5
Sel-AUC
StructU+Self-ConsU (TrueSkill+PageRank)
20.532
39.216
57.9
76.584
Jun 15, 2026
Sel-AUC
AUROC
Updated 1mo ago
Evaluation Results
Method
Method
Links
Sel-AUC
AUROC
StructU+Self-ConsU (TrueSkill+PageRank)
Model=DeepSeek R1, Sco...
2026.06
92.5
100
StructU+Self-ConsU (TrueSkill+PageRank)
Model=GPT-OSS 20B, Sco...
2026.06
89.7
100
StructU+Self-ConsU (TrueSkill+PageRank)
Model=Claude 4.5 Sonne...
2026.06
68.2
100
StructU+Self-ConsU (TrueSkill+PageRank)
Model=Qwen 3 32B, Scop...
2026.06
42.6
-
SemanticU
Model=Amazon Nova Premier
2026.06
29.4
-
StructU (TrueSkill+PageRank)
Model=Amazon Nova Prem...
2026.06
23.3
-
Feedback
Search any
task
Search any
task