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

Biomedical Reasoning on Biomni-Eval1

76.07Overall Accuracy

S1-NexusAgent

30.029241.982153.93565.8879Feb 2, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.02
76.07449094747070869076.7466
2026.02
66.934808074675886807336
2026.02
61.14288074685046707467.4454
2026.02
58.830807058635678703548
2026.02
55.730358652605078686038
2026.02
54.64007254636274626356
2026.02
42.421860423023.350727220.936
2026.02
34.6670522032070621626
2026.02
33.63106032243.3167674734
2026.02
31.826028167227672926