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

Coding Accuracy on LiveCodeBench V1-4

47.1Accuracy

Reasoning Memory

Updated 16d ago

Evaluation Results

Method	Links
Reasoning Memory 2026.04		47.1
Reasoning Memory 2026.04		46.2
Length Scaling 2026.04		40.5
Length Scaling 2026.04		39.9
No RAG 2026.04		38.7
Document RAG (Google) 2026.04		38.2
Reasoning Memory 2026.04		38.1
Reasoning Memory 2026.04		36.2
Length Scaling 2026.04		34.5
Length Scaling 2026.04		33.3
No RAG 2026.04		31.8
Template RAG (Self-Discover) 2026.04		31.2
Reasoning Memory 2026.04		31
Template RAG (ReasonFlux) 2026.04		30
Document RAG (CompactDS) 2026.04		29.2
Length Scaling 2026.04		28.2
Reasoning Memory 2026.04		27.8
Template RAG (Self-Discover) 2026.04		27.6
Trajectory RAG (Summary) 2026.04		26.7
Document RAG (CompactDS) 2026.04		26.7
Template RAG (ReasonFlux) 2026.04		26.2
Length Scaling 2026.04		25.5
Trajectory RAG (Prefix) 2026.04		24.9
Document RAG (Google) 2026.04		24.6
Trajectory RAG (Prefix) 2026.04		24.2
Trajectory RAG (Summary) 2026.04		24.2
Document RAG (Google) 2026.04		23.5
No RAG 2026.04		22
Template RAG (Self-Discover) 2026.04		21.3
Document RAG (CompactDS) 2026.04		20.8
Trajectory RAG (Prefix) 2026.04		19.5
Trajectory RAG (Summary) 2026.04		18.4
Template RAG (ReasonFlux) 2026.04		17.4