Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Medical Question Answering on NEJM
Loading...
73.13
Accuracy
m1-32B-1K
40.2348
48.7749
57.315
65.8551
Apr 1, 2025
May 22, 2025
Jul 13, 2025
Sep 3, 2025
Oct 25, 2025
Dec 16, 2025
Feb 6, 2026
Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
m1-32B-1K
Parameter Scale=32B, T...
2025.04
73.13
m1-7B-23K
Parameter Scale=7B, Th...
2025.04
64.34
MA-RAG-int
Backbone=Qwen3-8B, Ran...
2026.02
60.8
MA-RAG-ext
Backbone=Qwen3-8B, Ran...
2026.02
60.5
Multi-Refine
Backbone=Qwen3-8B
2026.02
58
TC-RAG
Backbone=Qwen3-8B
2026.02
57.7
SR-RAG
Backbone=Qwen3-8B
2026.02
57.6
FL-RAG
Backbone=Qwen3-8B
2026.02
57.2
SC
Backbone=Qwen3-8B
2026.02
56.6
CoT
Backbone=Qwen3-8B
2026.02
56.2
Qwen3-8B
Backbone=Qwen3-8B
2026.02
56
FLARE
Backbone=Qwen3-8B
2026.02
55.3
FS-RAG
Backbone=Qwen3-8B
2026.02
53.1
Llama-3.1-8B
Backbone=Llama-3.1-8B
2026.02
50.5
HuatuoGPT-o1-8B
Backbone=HuatuoGPT-o1-8B
2026.02
47.9
UltraMedical-3.1-8B
Backbone=UltraMedical-...
2026.02
41.5
Feedback
Search any
task
Search any
task