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

EndoAgentBench

Benchmarks

Task NameDataset NameSOTA ResultTrend
High-level Diagnostic ReasoningEndoAgentBench
CAP (CAR)76.03
8
Fine-grained PerceptionEndoAgentBench
Localization Classification Accuracy75.29
8
Showing 2 of 2 rows