Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Medical Question Answering on MedicationQA full n=674 (test)
Loading...
22
F1 Score
MedBioLM
13.68
15.84
18
20.16
May 25, 2026
F1 Score
ROUGE-L
Updated 8d ago
Evaluation Results
Method
Method
Links
F1 Score
ROUGE-L
MedBioLM
Setup=FT + RAG
2026.05
22
18.7
Qwen3-4B MedNLI-Cls
Setup=4B + RL
2026.05
19.1
15.3
Qwen3-4B Likelihood-NLI
Setup=4B + RL
2026.05
18.5
14.1
Qwen2.5-7B MedNLI-Cls
Setup=7B + RL
2026.05
17
14.4
GPT-4o (FT)
Setup=FT
2026.05
15.8
13.4
Qwen2.5-7B Likelihood-NLI
Setup=7B + RL
2026.05
15
13.7
Qwen2.5-7B GPT-NLI
Setup=7B + RL
2026.05
14.9
12.7
Qwen2.5-7B Hybrid
Setup=7B + RL
2026.05
14
12
Feedback
Search any
task
Search any
task