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

Correctness Prediction on TriviaQA

0.852AUROC

Assessor

0.4880.58250.6770.7715Aug 11, 2025Sep 18, 2025Oct 27, 2025Dec 5, 2025Jan 12, 2026Feb 20, 2026Mar 31, 2026
Updated 18d ago

Evaluation Results

MethodLinks
2025.09
0.852
2025.09
0.846
2025.09
0.826
2025.08
0.818
2025.08
0.812
2025.08
0.81
2025.09
0.807
2025.08
0.806
2025.09
0.804
2025.09
0.796
2025.08
0.796
2025.09
0.79
2025.09
0.789
2025.08
0.786
2025.08
0.783
2025.08
0.781
2025.08
0.774
2025.08
0.774
2025.08
0.773
2025.08
0.765
2025.09
0.759
2025.09
0.758
2025.08
0.754
2025.08
0.751
2025.08
0.751
2025.08
0.739
2025.08
0.736
2025.09
0.735
2025.09
0.734
2026.03
0.69
2025.08
0.683
2025.08
0.672
2025.09
0.643
2025.08
0.631
2025.09
0.619
2025.08
0.611
0.61
2026.03
0.6
2025.09
0.58
2025.09
0.57
0.55
0.52
2026.03
0.52
2025.09
0.515
2025.09
0.502