Share your thoughts, 1 month free Claude Pro on usSee more

Question Answering on BioASQ

98.32Accuracy

Fine-Tuned GPT-4o + MedBioRAG

Updated 1mo ago

Evaluation Results

Method	Links
Fine-Tuned GPT-4o + MedBioRAG 2025.12		98.32
GPT-4 + MedBioRAG 2025.12		97.79
Fine-Tuned GPT-4o 2025.12		97.06
GPT-4o + MedBioRAG 2025.12		97.06
GPT-4o-mini + MedBioRAG 2025.12		97.06
GPT-4o-mini 2025.12		96.32
GPT-4 2025.12		96.32
GPT-4o 2025.12		96.12
Galactica 2022.11		94.3
BLOOM 2022.11		91.4
GPT-3.5 2025.12		88.24
OPT 2022.11		81.4
TTARAG 2026.01		75
TTARAG 2026.01		71.8
GPT-3.5 + MedBioRAG 2025.12		66.91
USC 2024.10		61.5
USC 2024.10		61.5
ASTUTE RAG 2024.10		60.1
Self-Route 2024.10		59.1
USC 2024.10		58.4
ASTUTE RAG 2024.10		58.4
TTARAG 2026.01		58.4
RAG 2024.10		58
InstructRAG 2024.10		58
Self-Route 2024.10		58
ASTUTE RAG 2024.10		58
InstructRAG 2024.10		57.3
Self-Route 2024.10		57.3
GenRead 2024.10		57
RobustRAG 2024.10		56.3
RAG 2024.10		55.9
GenRead 2024.10		55.6
naive-rag 2026.01		55.6
In-Context Learning 2026.01		55.6
RAG 2024.10		55.2
Chain-of-Thought 2026.01		55.1
GenRead 2024.10		54.9
InstructRAG 2024.10		54.9
Chain-of-Thought 2026.01		54.6
naive-rag 2026.01		54.1
Provence 2025.03		54
RECOMP 2025.03		53
No compression 2025.03		53
No compression 2025.03		53
OSCAR-llama 2025.03		53
OSCAR-llama 2025.03		52
OSCAR-8-Layers 2025.03		52
OSCAR-llama 2025.03		52
Self-Route 2024.10		51.8
naive-rag 2026.01		51.4
No compression 2025.03		51
OSCAR-8-Layers 2025.03		51
In-Context Learning 2026.01		50.8
No RAG 2024.10		50.4
RobustRAG 2024.10		50.4
InstructRAG 2024.10		50.4
OSCAR-5-Layers 2025.03		50
In-Context Learning 2026.01		49.8
ASTUTE RAG 2024.10		49.3
RAG 2024.10		49
PISCO 2025.03		49
GenRead 2024.10		48.3
OSCAR-5-Layers 2025.03		46
No RAG 2024.10		45.8
Chain-of-Thought 2026.01		44.3
RobustRAG 2024.10		44.1
RobustRAG 2024.10		44.1
No RAG 2024.10		43.7
No RAG 2025.03		40
No compression 2025.03		40
USC 2024.10		36
No RAG 2024.10		34.3