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

Medical Visual Question Answering / Tool-use on ChestAgentBench OOD (test)

76.2Accuracy

Gemini-3-flash

45.41653.40861.469.392Mar 9, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.03
76.2
2026.03
72.7
2026.03
63.1
2026.03
62.8
2026.03
56.4
2026.03
53.3
2026.03
46.6