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

Clinical Question Answering on LiveMedBench (offline)

57.95Accuracy

SkeMex

29.3536.77544.251.625Jun 8, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.06
57.95
2026.06
54.79
2026.06
54.59
2026.06
54.29
2026.06
54.1
2026.06
53.97
2026.06
53.94
2026.06
53.76
2026.06
53.39
2026.06
53.2
2026.06
52.74
2026.06
52.15
2026.06
51.86
2026.06
50.39
2026.06
50.2
2026.06
50.07
2026.06
49.97
2026.06
49.17
2026.06
49.06
2026.06
49.01
2026.06
48.96
2026.06
48.9
2026.06
48.72
2026.06
48.69
2026.06
48.64
2026.06
48.44
2026.06
47.75
2026.06
47.61
2026.06
47.42
2026.06
47.26
2026.06
46.93
2026.06
44.93
2026.06
40.64
2026.06
39.26
2026.06
38.75
2026.06
37.72
2026.06
35.58
2026.06
30.45