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

MA

Benchmarks

Task NameDataset NameSOTA ResultTrend
Mathematical ReasoningMA
Accuracy91.3
20
ReasoningMA
Accuracy98.7
10
Road ExtractionMA
IoU20.3
9
Tabular Data ClusteringMA
ARI41.34
8
Malicious Behavior Defense in Multi-Agent SystemsMA PoisonRAG
ASR87
4
Showing 5 of 5 rows