Do Mixed-Vendor Multi-Agent LLMs Improve Clinical Diagnosis?

Research shows that multi-agent LLM systems using models from different vendors (o4-mini, Gemini-2.5-Pro, Claude-4.5-Sonnet) significantly outperform single-vendor teams in clinical diagnosis tasks. Mixed-vendor configurations achieve superior recall and accuracy by combining complementary strengths and reducing shared biases that affect homogeneous model teams.

• →Mixed-vendor multi-agent LLM teams consistently outperform single-vendor configurations in clinical diagnosis accuracy.
• →Vendor diversity helps pool complementary inductive biases and surface correct diagnoses that individual models miss.
• →Single-vendor teams risk correlated failure modes that reinforce shared biases rather than correcting them.
• →The research achieved state-of-the-art results on RareBench and DiagnosisArena medical diagnosis benchmarks.
• →Vendor diversity emerges as a key design principle for building robust clinical diagnostic AI systems.