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

Question Answering on MMLU Med

90.6Accuracy

HCQR

33.81648.55863.378.042Mar 19, 2026Mar 25, 2026Apr 1, 2026Apr 8, 2026Apr 14, 2026Apr 21, 2026Apr 28, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.03
90.6-
2026.03
90.2-
2026.03
90.1-
2026.03
89.4-
2026.03
88.9-
2026.03
88.8-
2026.03
88.2-
2026.03
85.4-
2026.03
82.9-
2026.03
82.6-
2026.03
82.5-
2026.03
82.3-
2026.03
81.8-
2026.03
81.2-
2026.03
79.7-
2026.03
76.5-
2026.03
75.8-
2026.03
75.7-
2026.03
75-
2026.03
74.7-
2026.03
74.7-
2026.04
71.33-
2026.03
68.6-
2026.03
67.8-
2026.03
67.1-
2026.03
67-
2026.03
67-
2026.03
66.3-
2026.04
65.33-
2026.03
64.5-
2026.04
51.67-
2026.04
50-
2026.04
45.67-
2026.04
36-
2026.03
-78.6
2026.03
-77.5
2026.03
-78.8
2026.03
-78.2
2026.03
-79.1
2026.03
-78
2026.03
-81.1