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

Error prediction on NCQA (test)

99.2AUROC

Llama-3.1-8B

46.99260.54674.187.654Jun 1, 2026
Updated 1d ago

Evaluation Results

MethodLinks
2026.06
99.2-
2026.06
99.2-
2026.06
99.1-
2026.06
99.1-
2026.06
98.9-
2026.06
98.8-
2026.06
98.5-
2026.06
98.4-
2026.06
98.3-
2026.06
98.2-
2026.06
97-
2026.06
93.8-
2026.06
93.1-
2026.06
92.7-
2026.06
91.8-
2026.06
84.6-
2026.06
83.7-
2026.06
79.4-
2026.06
77.6-
2026.06
76.8-
2026.06
76.8-
2026.06
76.6-
2026.06
76.5-
2026.06
75.2-
2026.06
74.8-
73.9-
2026.06
73.7-
2026.06
73-
2026.06
72.3-
2026.06
72.2-
2026.06
71.8-
2026.06
70.8-
2026.06
70.4-
2026.06
69.9-
2026.06
69-
2026.06
68.7-
2026.06
68.6-
2026.06
68.3-
2026.06
68-
2026.06
67.6-
2026.06
67.2-
2026.06
66.7-
2026.06
66.7-
2026.06
66.5-
2026.06
66.2-
2026.06
65.5-
2026.06
65.2-
2026.06
64.9-
2026.06
64.9-
2026.06
64.6-
2026.06
63.9-
2026.06
63.7-
2026.06
63.6-
2026.06
63.2-
2026.06
62-
2026.06
61.8-
2026.06
61.5-
2026.06
61-
2026.06
60.9-
2026.06
60.5-
2026.06
60.4-
2026.06
59.9-
2026.06
59.8-
2026.06
59.1-
2026.06
59-
2026.06
58.4-
2026.06
58.1-
2026.06
57.8-
2026.06
57.8-
2026.06
56.9-
2026.06
56.9-
2026.06
54.7-
2026.06
54.2-
2026.06
52.9-
2026.06
50.8-
2026.06
49-
2026.06
-0.499
2026.06
-0.577
2026.06
-0.967
2026.06
-0.534
2026.06
-0.973
2026.06
-0.476
2026.06
-0.606
2026.06
-0.963
2026.06
-0.52
2026.06
-0.964
2026.06
-0.468
2026.06
-0.489
2026.06
-0.971
2026.06
-0.436
2026.06
-0.972
2026.06
-0.086
2026.06
-0.533
2026.06
-0.968
2026.06
--0.545
2026.06
-0.956
2026.06
-0.684
2026.06
-0.644
2026.06
-0.984
2026.06
--0.319
Showing 100 of 111 rows