List your company

Medical Question Answering on MedQA In-Distribution

92.19AccuracySkillFlow
68.623674.741880.8686.9782May 13, 2026

Evaluation results

MethodLinks
SkillFlowMethod Category=Ours2026.0592.19
FlowSteerMethod Category=Agent+RL2026.0590.63
Qwen3.5-AFlowMethod Category=AFlow, Backbone=Qwen3.52026.0589.84
AgentFlowMethod Category=Agent+RL2026.0587.5
SkillRLMethod Category=Agent+RL2026.0585.94
v4-flashMethod Category=Baseline2026.0583.59
Qwen3.5-GRPOMethod Category=GRPO, Backbone=Qwen3.52026.0577.34
Qwen3.5-SFTMethod Category=SFT, Backbone=Qwen3.52026.0573.44
Qwen3.5-9BMethod Category=Baseline2026.0569.53