Share your thoughts, 1 month free Claude Pro on usSee more

Uncertainty Estimation on HumanEval

0.886AUROC

Top-5 + Tests + Pseudo

Updated 1mo ago

Evaluation Results

Method
Top-5 + Tests + Pseudo 2026.06	0.886	0.99
Top-5 + Tests + Pseudo 2026.06	0.886	0.99
Generated Tests (FUNC) 2026.06	0.861	0.952
Generated Tests (FUNC) 2026.06	0.861	0.952
Top-5 + Tests + Pseudo 2026.06	0.852	0.983
Top-5 + Tests + Pseudo 2026.06	0.852	0.983
Top-5 + Tests + Pseudo 2026.06	0.842	0.957
Top-5 + Tests + Pseudo 2026.06	0.842	0.957
Generated Tests (FUNC) 2026.06	0.822	0.958
Generated Tests (FUNC) 2026.06	0.822	0.958
Generated Tests (FUNC) 2026.06	0.819	0.94
Generated Tests (FUNC) 2026.06	0.819	0.94
Pseudo Consistency (ALGO) 2026.06	0.768	0.939
Pseudo Consistency (ALGO) 2026.06	0.768	0.939
Pseudo Consistency (ALGO) 2026.06	0.759	0.832
Pseudo Consistency (ALGO) 2026.06	0.759	0.832
Generated Tests (FUNC) 2026.06	0.756	0.938
Top-5 Entropy (LEX) 2026.06	0.749	0.934
Top-5 Entropy (LEX) 2026.06	0.749	0.934
Top-5 + Tests + Pseudo 2026.06	0.746	0.98
Consistency (VR) 2026.06	0.741	0.955
Consistency (VR) 2026.06	0.741	0.955
Top-5 + Tests + Pseudo 2026.06	0.734	0.944
Generated Tests (FUNC) 2026.06	0.734	0.973
Top-5 Entropy (LEX) 2026.06	0.729	0.952
Top-5 Entropy (LEX) 2026.06	0.729	0.952
Pseudo Consistency (ALGO) 2026.06	0.718	0.947
Pseudo Consistency (ALGO) 2026.06	0.718	0.947
Mean Entropy 2026.06	0.715	0.941
Mean Entropy 2026.06	0.715	0.941
Consistency (BLEU) 2026.06	0.705	0.981
Consistency (BLEU) 2026.06	0.694	0.945
Consistency (BLEU) 2026.06	0.694	0.945
Max Probability 2026.06	0.68	0.902
Max Entropy 2026.06	0.678	0.977
Mean Probability 2026.06	0.675	0.889
Symb. Clustering 2026.06	0.673	0.943
Symb. Clustering 2026.06	0.673	0.943
Pseudo Consistency (ALGO) 2026.06	0.671	0.973
Symb. Clustering 2026.06	0.668	0.893
Symb. Clustering 2026.06	0.668	0.893
Max Probability 2026.06	0.667	0.96
Mean Probability 2026.06	0.662	0.951
Symb. Clustering 2026.06	0.654	0.922
Symb. Clustering 2026.06	0.646	0.895
Symb. Clustering 2026.06	0.646	0.895
Consistency (VR) 2026.06	0.644	0.875
Consistency (VR) 2026.06	0.644	0.875
Consistency (VR) 2026.06	0.635	0.877
Consistency (VR) 2026.06	0.635	0.877
Max Probability 2026.06	0.63	0.935
Pseudo Consistency (ALGO) 2026.06	0.621	0.915
Mean Probability 2026.06	0.619	0.902
Max Entropy 2026.06	0.619	0.881
Consistency (BLEU) 2026.06	0.616	0.885
Consistency (BLEU) 2026.06	0.616	0.885
Top-5 Entropy (LEX) 2026.06	0.613	0.902
Mean Entropy 2026.06	0.612	0.876
Mean Entropy 2026.06	0.612	0.876
Max Entropy 2026.06	0.601	0.898
Top-5 Entropy (LEX) 2026.06	0.591	0.967
Consistency (BLEU) 2026.06	0.586	0.85
Consistency (BLEU) 2026.06	0.586	0.85
Mean Entropy 2026.06	0.581	0.957
Consistency (VR) 2026.06	0.578	0.962
Consistency (VR) 2026.06	0.574	0.898
Max Probability 2026.06	0.549	0.899
Mean Probability 2026.06	0.53	0.9
Max Entropy 2026.06	0.523	0.889
Symb. Clustering 2026.06	0.517	0.96
Consistency (BLEU) 2026.06	0.516	0.885
Mean Entropy 2026.06	0.49	0.868
Top-5 Entropy (LEX) 2026.06	0.466	0.827
Top-5 Entropy (LEX) 2026.06	0.466	0.827
Max Probability 2026.06	0.425	0.788
Max Entropy 2026.06	0.412	0.826
Mean Probability 2026.06	0.393	0.767
Mean Entropy 2026.06	0.376	0.798
Mean Entropy 2026.06	0.376	0.798