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

Code on LiveCodeBench V5-6

50.8Accuracy

Reasoning Memory

Updated 16d ago

Evaluation Results

Method	Links
Reasoning Memory 2026.04		50.8
Reasoning Memory 2026.04		50.3
Length Scaling 2026.04		47.6
No RAG 2026.04		46.5
Length Scaling 2026.04		44.4
Trajectory RAG (Prefix) 2026.04		43.2
Document RAG (Google) 2026.04		42.6
Trajectory RAG (Summary) 2026.04		41.8
Reasoning Memory 2026.04		41.2
Reasoning Memory 2026.04		39.7
Length Scaling 2026.04		34.4
Length Scaling 2026.04		34.3
Template RAG (Self-Discover) 2026.04		33.9
Reasoning Memory 2026.04		32.5
Length Scaling 2026.04		30.2
Reasoning Memory 2026.04		29.2
Document RAG (CompactDS) 2026.04		28.4
Template RAG (Self-Discover) 2026.04		27.9
Length Scaling 2026.04		27.8
Template RAG (ReasonFlux) 2026.04		27.8
Template RAG (ReasonFlux) 2026.04		26.8
No RAG 2026.04		26.6
Trajectory RAG (Summary) 2026.04		26
Document RAG (CompactDS) 2026.04		25.8
Trajectory RAG (Prefix) 2026.04		24.9
Template RAG (Self-Discover) 2026.04		24.7
Document RAG (Google) 2026.04		23.1
Document RAG (Google) 2026.04		22.8
No RAG 2026.04		21.1
Template RAG (ReasonFlux) 2026.04		21
Document RAG (CompactDS) 2026.04		17.2
Trajectory RAG (Prefix) 2026.04		12.8
Trajectory RAG (Summary) 2026.04		12.1