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

Uncertainty Estimation on MBPP

0.791AUROC

Top-5 + Tests + Pseudo

Updated 1mo ago

Evaluation Results

Method
Top-5 + Tests + Pseudo 2026.06	0.791	0.785
Top-5 + Tests + Pseudo 2026.06	0.791	0.785
Generated Tests (FUNC) 2026.06	0.776	0.735
Generated Tests (FUNC) 2026.06	0.776	0.735
Top-5 + Tests + Pseudo 2026.06	0.748	0.767
Top-5 + Tests + Pseudo 2026.06	0.746	0.761
Top-5 + Tests + Pseudo 2026.06	0.746	0.761
Generated Tests (FUNC) 2026.06	0.741	0.736
Generated Tests (FUNC) 2026.06	0.741	0.736
Top-5 + Tests + Pseudo 2026.06	0.74	0.755
Top-5 + Tests + Pseudo 2026.06	0.74	0.755
Generated Tests (FUNC) 2026.06	0.731	0.722
Generated Tests (FUNC) 2026.06	0.73	0.702
Generated Tests (FUNC) 2026.06	0.73	0.702
Top-5 + Tests + Pseudo 2026.06	0.727	0.738
Pseudo Consistency (ALGO) 2026.06	0.722	0.636
Pseudo Consistency (ALGO) 2026.06	0.722	0.636
Generated Tests (FUNC) 2026.06	0.711	0.724
Consistency (VR) 2026.06	0.663	0.713
Symb. Clustering 2026.06	0.661	0.691
Symb. Clustering 2026.06	0.661	0.691
Consistency (VR) 2026.06	0.648	0.684
Consistency (VR) 2026.06	0.648	0.684
Pseudo Consistency (ALGO) 2026.06	0.647	0.62
Pseudo Consistency (ALGO) 2026.06	0.647	0.62
Consistency (BLEU) 2026.06	0.64	0.673
Consistency (BLEU) 2026.06	0.64	0.673
Max Probability 2026.06	0.617	0.634
Consistency (VR) 2026.06	0.616	0.639
Top-5 Entropy (LEX) 2026.06	0.616	0.653
Consistency (VR) 2026.06	0.616	0.639
Top-5 Entropy (LEX) 2026.06	0.616	0.653
Pseudo Consistency (ALGO) 2026.06	0.615	0.65
Pseudo Consistency (ALGO) 2026.06	0.615	0.65
Top-5 Entropy (LEX) 2026.06	0.614	0.653
Top-5 Entropy (LEX) 2026.06	0.614	0.653
Consistency (VR) 2026.06	0.611	0.642
Consistency (VR) 2026.06	0.611	0.642
Pseudo Consistency (ALGO) 2026.06	0.611	0.656
Consistency (BLEU) 2026.06	0.603	0.664
Pseudo Consistency (ALGO) 2026.06	0.602	0.66
Max Entropy 2026.06	0.601	0.62
Consistency (BLEU) 2026.06	0.6	0.619
Top-5 Entropy (LEX) 2026.06	0.599	0.629
Consistency (BLEU) 2026.06	0.597	0.621
Consistency (BLEU) 2026.06	0.597	0.621
Mean Probability 2026.06	0.596	0.612
Consistency (BLEU) 2026.06	0.596	0.641
Consistency (BLEU) 2026.06	0.596	0.641
Top-5 Entropy (LEX) 2026.06	0.592	0.657
Symb. Clustering 2026.06	0.592	0.616
Mean Entropy 2026.06	0.585	0.627
Mean Probability 2026.06	0.58	0.658
Max Probability 2026.06	0.573	0.66
Top-5 Entropy (LEX) 2026.06	0.57	0.616
Top-5 Entropy (LEX) 2026.06	0.57	0.616
Max Entropy 2026.06	0.57	0.607
Symb. Clustering 2026.06	0.565	0.639
Symb. Clustering 2026.06	0.565	0.639
Symb. Clustering 2026.06	0.56	0.66
Mean Entropy 2026.06	0.544	0.611
Mean Entropy 2026.06	0.544	0.611
Mean Entropy 2026.06	0.544	0.617
Max Probability 2026.06	0.536	0.609
Max Probability 2026.06	0.535	0.57
Max Entropy 2026.06	0.532	0.569
Max Entropy 2026.06	0.532	0.563
Max Entropy 2026.06	0.532	0.632
Mean Probability 2026.06	0.529	0.561
Mean Entropy 2026.06	0.528	0.558
Mean Entropy 2026.06	0.528	0.558
Consistency (VR) 2026.06	0.528	0.56
Mean Entropy 2026.06	0.526	0.565
Mean Entropy 2026.06	0.526	0.565
Max Probability 2026.06	0.521	0.564
Mean Probability 2026.06	0.518	0.555
Symb. Clustering 2026.06	0.514	0.575
Symb. Clustering 2026.06	0.514	0.575
Mean Probability 2026.06	0.51	0.61