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

Medical Question Answering on MMLU-P

97.1Accuracy

GPT-4.1-mini

Updated 1mo ago

Evaluation Results

Method	Links
GPT-4.1-mini 2026.02		97.1
Gemini 2.5 2026.02		97.1
DeepSeek-Chat 2026.02		91
Gemini 2.5 2026.02		90.5
GPT-4.1-mini 2026.02		88.7
Gemini 2.5 2026.02		87.5
DeepSeek-Chat 2026.02		87.5
GPT-4.1-mini 2026.02		86.8
DeepSeek-Chat 2026.02		85.7
m1-32B-1K 2025.04		76.94
MA-RAG-int 2026.02		70.9
MA-RAG-ext 2026.02		70.7
Multi-Refine 2026.02		69.1
SC 2026.02		66.5
SR-RAG 2026.02		66.1
m1-7B-23K 2025.04		65.86
m1-7B-1K 2025.04		65.15
Qwen3-8B 2026.02		64.9
FL-RAG 2026.02		64.1
TC-RAG 2026.02		63.6
CoT 2026.02		63.4
FLARE 2026.02		62.2
FS-RAG 2026.02		59.5
Llama-3.1-8B 2026.02		58
MedLlama3-8B-v2 2025.04		55.11
HuatuoGPT-o1-8B 2026.02		54
OpenBioLLM-8B 2025.04		49.32
UltraMedical-3.1-8B 2026.02		48.5
MedLlama3-8B-v1 2025.04		27.43