List your company
ResearchFormerly WizWand

Medical Question Answering on BioASQ

88.67AccuracySEMA-RAG
32.30246.93661.5776.204Feb 13, 2026Feb 28, 2026Mar 15, 2026Mar 31, 2026Apr 15, 2026Apr 30, 2026May 16, 2026
Updated 5mo ago

Evaluation results

MethodLinks
SEMA-RAGBackbone=kimi-k22026.0588.67
SEMA-RAGBackbone=gemini-2.0-flash2026.0588.19
CoTBackbone=kimi-k22026.0585.76
MedRAGBackbone=kimi-k22026.0585.6
i-MedRAGBackbone=kimi-k22026.0583.17
SEMA-RAGBackbone=qwen3-coder-plus2026.0583.01
SEMA-RAGBackbone=deepseek-v3.12026.0582.85
i-MedRAGBackbone=qwen3-coder-plus2026.0582.52
CoTBackbone=qwen3-coder-plus2026.0581.72
MedCPTBackbone=kimi-k22026.0581.39
ReFilterBackbone=Qwen2.5-14B-Instruct, Zero-shot evaluation=true2026.0280.74
CHRGenerator=Gemma-2-9B-It, Hypothesis Generator=Qwen2.5-72B-Instruct, Retriever=MedCPT, Corpus=MedCorp2026.0480.7
i-MedRAGBackbone=deepseek-v3.12026.0580.58
CoTBackbone=deepseek-v3.12026.0580.1
S-RAGBackbone=Qwen2.5-14B-Instruct, Zero-shot evaluation=true2026.0279.29
DyPRAGBackbone=Qwen2.5-14B-Instruct, Zero-shot evaluation=true2026.0279.29
PRAGBackbone=Qwen2.5-14B-Instruct, Zero-shot evaluation=true2026.0279.13
ReFilterBackbone=LLaMA-3-8B-Instruct, Zero-shot evaluation=true2026.0278.8
MedRAGBackbone=deepseek-v3.12026.0578.48
VanillaBackbone=Qwen2.5-14B-Instruct, Zero-shot evaluation=true2026.0278.16
i-MedRAGBackbone=gemini-2.0-flash2026.0577.99
S-RAGBackbone=LLaMA-3-8B-Instruct, Zero-shot evaluation=true2026.0277.18
VanillaBackbone=LLaMA-3-8B-Instruct, Zero-shot evaluation=true2026.0276.54
MedCPTBackbone=deepseek-v3.12026.0576.38
PRAGBackbone=LLaMA-3-8B-Instruct, Zero-shot evaluation=true2026.0276.05
DyPRAGBackbone=LLaMA-3-8B-Instruct, Zero-shot evaluation=true2026.0275.89
MedCPTBackbone=qwen3-coder-plus2026.0575.89
CHRGenerator=Qwen2.5-7B-Instruct, Hypothesis Generator=Qwen2.5-72B-Instruct, Retriever=MedCPT, Corpus=MedCorp2026.0475.6
Standard RAGGenerator=Gemma-2-9B-It, Hypothesis Generator=Qwen2.5-72B-Instruct, Retriever=MedCPT, Corpus=MedCorp2026.0474.3
SEMA-RAGBackbone=glm-4.0-flash2026.0572.98
MedRAGBackbone=gemini-2.0-flash2026.0572.65
MedRAGBackbone=qwen3-coder-plus2026.0572.33
CSQEGenerator=Gemma-2-9B-It, Hypothesis Generator=Qwen2.5-72B-Instruct, Retriever=MedCPT, Corpus=MedCorp2026.0472.2
ReFilterBackbone=Qwen2.5-1.5B-Instruct, Zero-shot evaluation=true2026.0271.04
MedCPTBackbone=gemini-2.0-flash2026.0570.06
PRAGBackbone=Qwen2.5-1.5B-Instruct, Zero-shot evaluation=true2026.0269.9
CoTBackbone=gemini-2.0-flash2026.0568.45
DyPRAGBackbone=Qwen2.5-1.5B-Instruct, Zero-shot evaluation=true2026.0267.96
VanillaBackbone=Qwen2.5-1.5B-Instruct, Zero-shot evaluation=true2026.0266.18
S-RAGBackbone=Qwen2.5-1.5B-Instruct, Zero-shot evaluation=true2026.0266.18
Query2docGenerator=Qwen2.5-7B-Instruct, Hypothesis Generator=Qwen2.5-72B-Instruct, Retriever=MedCPT, Corpus=MedCorp2026.0465.2
i-MedRAGBackbone=glm-4.0-flash2026.0564.72
CHRGenerator=Llama-3-8B-Instruct, Hypothesis Generator=Qwen2.5-72B-Instruct, Retriever=MedCPT, Corpus=MedCorp2026.0463.1
MedRAGBackbone=glm-4.0-flash2026.0562.78
MedCPTBackbone=glm-4.0-flash2026.0560.84
Standard RAGGenerator=Qwen2.5-7B-Instruct, Hypothesis Generator=Qwen2.5-72B-Instruct, Retriever=MedCPT, Corpus=MedCorp2026.0460.5
CoTBackbone=glm-4.0-flash2026.0558.9
Query2docGenerator=Gemma-2-9B-It, Hypothesis Generator=Qwen2.5-72B-Instruct, Retriever=MedCPT, Corpus=MedCorp2026.0458.6
CSQEGenerator=Llama-3-8B-Instruct, Hypothesis Generator=Qwen2.5-72B-Instruct, Retriever=MedCPT, Corpus=MedCorp2026.0456.5
ThinkQEGenerator=Llama-3-8B-Instruct, Hypothesis Generator=Qwen2.5-72B-Instruct, Retriever=MedCPT, Corpus=MedCorp2026.0452.1
HyDE (H+ only)Generator=Llama-3-8B-Instruct, Hypothesis Generator=Qwen2.5-72B-Instruct, Retriever=MedCPT, Corpus=MedCorp2026.0451.3
HyDE (H+ only)Generator=Gemma-2-9B-It, Hypothesis Generator=Qwen2.5-72B-Instruct, Retriever=MedCPT, Corpus=MedCorp2026.0448.4
Query2docGenerator=Llama-3-8B-Instruct, Hypothesis Generator=Qwen2.5-72B-Instruct, Retriever=MedCPT, Corpus=MedCorp2026.0446.9
CSQEGenerator=Qwen2.5-7B-Instruct, Hypothesis Generator=Qwen2.5-72B-Instruct, Retriever=MedCPT, Corpus=MedCorp2026.0444.8
ThinkQEGenerator=Gemma-2-9B-It, Hypothesis Generator=Qwen2.5-72B-Instruct, Retriever=MedCPT, Corpus=MedCorp2026.0444.5
ThinkQEGenerator=Qwen2.5-7B-Instruct, Hypothesis Generator=Qwen2.5-72B-Instruct, Retriever=MedCPT, Corpus=MedCorp2026.0443.4
HyDE (H+ only)Generator=Qwen2.5-7B-Instruct, Hypothesis Generator=Qwen2.5-72B-Instruct, Retriever=MedCPT, Corpus=MedCorp2026.0442.2
Standard RAGGenerator=Llama-3-8B-Instruct, Hypothesis Generator=Qwen2.5-72B-Instruct, Retriever=MedCPT, Corpus=MedCorp2026.0441.8
ReFilterBackbone=LLaMA-3.2-1B-Instruct, Zero-shot evaluation=true2026.0237.22
VanillaBackbone=LLaMA-3.2-1B-Instruct, Zero-shot evaluation=true2026.0236.57
PRAGBackbone=LLaMA-3.2-1B-Instruct, Zero-shot evaluation=true2026.0235.44
DyPRAGBackbone=LLaMA-3.2-1B-Instruct, Zero-shot evaluation=true2026.0235.11
S-RAGBackbone=LLaMA-3.2-1B-Instruct, Zero-shot evaluation=true2026.0234.47