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

Multi-agent Question Answering on MedQA (first 300 questions)

44.55Average Accuracy

TextFullT

32.194835.402438.6141.8176May 25, 2026
Updated 8d ago

Evaluation Results

MethodLinks
2026.05
44.5544.67505.035.47
2026.05
44.11461,717.618.18
2026.05
42.6742.671,247.513.15
2026.05
42.5643.331,137.8911.58
2026.05
42.1142.33570.7
2026.05
42.1142.3372.011.47
2026.05
41.8942.67960.2610.04
2026.05
40.7841.671,316.214.48
2026.05
38.3338.33113.591.25
2026.05
32.6733324.433.61