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

Medical Question Answering on MedAgentsBench

59.55MedBullets Score

GSEM

38.510843.972949.43554.8971Mar 23, 2026
Updated 25d ago

Evaluation Results

MethodLinks
2026.03
59.5577.0241294169.24
2026.03
58.4376.836214164.25
2026.03
55.0674.6241274066.74
2026.03
53.9376.836213059.94
2026.03
52.817243213061
2026.03
52.8171.9938233665.46
2026.03
51.6976.3835263667.2
2026.03
50.5674.6237292763.19
2026.03
50.5676.3743243565.38
2026.03
49.4374.8441342770.9
2026.03
48.3174.6240283164.78
2026.03
48.3172.4336263269.01
2026.03
47.1974.8438292768.56
2026.03
47.1974.1837272768.03
2026.03
43.8270.7230241966.06
2026.03
42.768.9338272465.61
2026.03
40.4560.6124132256.01
2026.03
39.3273.7436262962.96