Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Medical Question Answering on MedQA In-Distribution
Loading...
92.19
Accuracy
SkillFlow
68.6236
74.7418
80.86
86.9782
May 13, 2026
Accuracy
Updated 19d ago
Evaluation Results
Method
Method
Links
Accuracy
SkillFlow
Method Category=Ours
2026.05
92.19
FlowSteer
Method Category=Agent+RL
2026.05
90.63
Qwen3.5-AFlow
Method Category=AFlow,...
2026.05
89.84
AgentFlow
Method Category=Agent+RL
2026.05
87.5
SkillRL
Method Category=Agent+RL
2026.05
85.94
v4-flash
Method Category=Baseline
2026.05
83.59
Qwen3.5-GRPO
Method Category=GRPO,...
2026.05
77.34
Qwen3.5-SFT
Method Category=SFT, B...
2026.05
73.44
Qwen3.5-9B
Method Category=Baseline
2026.05
69.53
Feedback
Search any
task
Search any
task