List your company

Medical Diagnosis on MIMIC-IV (test)

78.33AccuracyGLEAN (N=3)
52.818859.441966.06572.6881Mar 3, 2026

Evaluation results

MethodLinks
GLEAN (N=3)Agent Backbone=Qwen3-30B, Selection Strategy=BoN-162026.0378.33
GLEAN (N=3)Agent Backbone=Qwen3-30B, Selection Strategy=BoN-82026.0376.71
GLEAN (N=3)Agent Backbone=Qwen2.5-7B, Selection Strategy=BoN-162026.0376.6
GLEAN (N=3)Agent Backbone=Qwen2.5-7B, Selection Strategy=BoN-82026.0374.29
GLEAN (N=3)Agent Backbone=Qwen3-30B, Selection Strategy=BoN-42026.0373.83
GLEAN (N=1)Agent Backbone=Qwen2.5-7B, Selection Strategy=BoN-162026.0373.6
GLEAN (N=1)Agent Backbone=Qwen2.5-7B, Selection Strategy=BoN-82026.0373.01
RAGAgent Backbone=Qwen2.5-7B, Selection Strategy=BoN-162026.0372.4
GLEAN (N=1)Agent Backbone=Qwen3-30B, Selection Strategy=BoN-82026.0372.37
GLEAN (N=1)Agent Backbone=Qwen3-30B, Selection Strategy=BoN-42026.0371.98
GLEAN (N=1)Agent Backbone=Qwen3-30B, Selection Strategy=BoN-162026.0371.67
RAGAgent Backbone=Qwen2.5-7B, Selection Strategy=BoN-82026.0371.4
GLEAN (N=3)Agent Backbone=Qwen2.5-7B, Selection Strategy=BoN-42026.0370.52
Self-ConsistencyAgent Backbone=Qwen3-30B, Selection Strategy=BoN-162026.0370
ORMAgent Backbone=Qwen3-30B, Selection Strategy=BoN-82026.0369.99
GLEAN (N=1)Agent Backbone=Qwen2.5-7B, Selection Strategy=BoN-42026.0369.96
ORMAgent Backbone=Qwen3-30B, Selection Strategy=BoN-162026.0369.66
Self-ConsistencyAgent Backbone=Qwen2.5-7B, Selection Strategy=BoN-162026.0369.4
RAGAgent Backbone=Qwen3-30B, Selection Strategy=BoN-82026.0369.33
RAGAgent Backbone=Qwen3-30B, Selection Strategy=BoN-42026.0369.01
RAGAgent Backbone=Qwen3-30B, Selection Strategy=BoN-162026.0369
RAGAgent Backbone=Qwen2.5-7B, Selection Strategy=BoN-42026.0368.91
Self-ConsistencyAgent Backbone=Qwen3-30B, Selection Strategy=BoN-82026.0368.65
ORMAgent Backbone=Qwen3-30B, Selection Strategy=BoN-42026.0368.01
Self-VerificationAgent Backbone=Qwen3-30B, Selection Strategy=BoN-42026.0367.43
Self-ConsistencyAgent Backbone=Qwen2.5-7B, Selection Strategy=BoN-82026.0366.17
Self-VerificationAgent Backbone=Qwen3-30B, Selection Strategy=BoN-82026.0366.17
MedPRMAgent Backbone=Qwen3-30B, Selection Strategy=BoN-162026.0366
MedPRMAgent Backbone=Qwen3-30B, Selection Strategy=BoN-82026.0365.82
Self-ConsistencyAgent Backbone=Qwen3-30B, Selection Strategy=BoN-42026.0365.25
Self-VerificationAgent Backbone=Qwen2.5-7B, Selection Strategy=BoN-82026.0364.74
MedPRMAgent Backbone=Qwen3-30B, Selection Strategy=BoN-42026.0364.68
LLM-as-a-JudgeAgent Backbone=Qwen3-30B, Selection Strategy=BoN-162026.0364.67
Self-VerificationAgent Backbone=Qwen2.5-7B, Selection Strategy=BoN-162026.0364.4
ORMAgent Backbone=Qwen2.5-7B, Selection Strategy=BoN-162026.0364.4
LLM-as-a-JudgeAgent Backbone=Qwen3-30B, Selection Strategy=BoN-42026.0364.24
LLM-as-a-JudgeAgent Backbone=Qwen3-30B, Selection Strategy=BoN-82026.0363.96
Self-VerificationAgent Backbone=Qwen2.5-7B, Selection Strategy=BoN-42026.0363.66
P(True)Agent Backbone=Qwen3-30B, Selection Strategy=BoN-42026.0363.22
P(True)Agent Backbone=Qwen3-30B, Selection Strategy=BoN-82026.0362.45
Self-ConsistencyAgent Backbone=Qwen2.5-7B, Selection Strategy=BoN-42026.0362.09
LLM-as-a-JudgeAgent Backbone=Qwen2.5-7B, Selection Strategy=BoN-162026.0362
Self-VerificationAgent Backbone=Qwen3-30B, Selection Strategy=BoN-162026.0362
ORMAgent Backbone=Qwen2.5-7B, Selection Strategy=BoN-82026.0361.59
P(True)Agent Backbone=Qwen3-30B, Selection Strategy=BoN-162026.0361.33
LLM-as-a-JudgeAgent Backbone=Qwen2.5-7B, Selection Strategy=BoN-82026.0360.62
ORMAgent Backbone=Qwen2.5-7B, Selection Strategy=BoN-42026.0359.65
MedPRMAgent Backbone=Qwen2.5-7B, Selection Strategy=BoN-162026.0358.4
LLM-as-a-JudgeAgent Backbone=Qwen2.5-7B, Selection Strategy=BoN-42026.0358.18
MedPRMAgent Backbone=Qwen2.5-7B, Selection Strategy=BoN-82026.0357.77
MedPRMAgent Backbone=Qwen2.5-7B, Selection Strategy=BoN-42026.0357.23
P(True)Agent Backbone=Qwen2.5-7B, Selection Strategy=BoN-82026.0354.02
P(True)Agent Backbone=Qwen2.5-7B, Selection Strategy=BoN-42026.0353.86
P(True)Agent Backbone=Qwen2.5-7B, Selection Strategy=BoN-162026.0353.8