Coding Accuracy on LiveCodeBench V1-4
47.1AccuracyReasoning Memory
Evaluation Results
| Method | Links | |
|---|---|---|
| Reasoning MemoryBackbone=Qwen3-32B, Ret.=Proc., m=302026.04 | 47.1 | |
| Reasoning MemoryBackbone=Qwen3-32B, Ret.=Proc., m=82026.04 | 46.2 | |
| Length ScalingBackbone=Qwen3-32B, Ret.=N/A, m=302026.04 | 40.5 | |
| Length ScalingBackbone=Qwen3-32B, Ret.=N/A, m=82026.04 | 39.9 | |
| No RAGBackbone=Qwen3-32B, Ret.=N/A, m=82026.04 | 38.7 | |
| Document RAG (Google)Backbone=Qwen3-32B, Ret.=Fact., m=82026.04 | 38.2 | |
| Reasoning MemoryBackbone=OpenThinker3-7B, Ret.=Proc., m=302026.04 | 38.1 | |
| Reasoning MemoryBackbone=OpenThinker3-7B, Ret.=Proc., m=82026.04 | 36.2 | |
| Length ScalingBackbone=OpenThinker3-7B, Ret.=N/A, m=302026.04 | 34.5 | |
| Length ScalingBackbone=OpenThinker3-7B, Ret.=N/A, m=82026.04 | 33.3 | |
| No RAGBackbone=OpenThinker3-7B, Ret.=N/A, m=82026.04 | 31.8 | |
| Template RAG (Self-Discover)Backbone=Qwen3-32B, Ret.=Proc., m=82026.04 | 31.2 | |
| Reasoning MemoryBackbone=DeepSeek-R1-Distill-Llama-8B, Ret.=Proc., m=302026.04 | 31 | |
| Template RAG (ReasonFlux)Backbone=Qwen3-32B, Ret.=Proc., m=82026.04 | 30 | |
| Document RAG (CompactDS)Backbone=OpenThinker3-7B, Ret.=Fact., m=82026.04 | 29.2 | |
| Length ScalingBackbone=DeepSeek-R1-Distill-Llama-8B, Ret.=N/A, m=302026.04 | 28.2 | |
| Reasoning MemoryBackbone=DeepSeek-R1-Distill-Llama-8B, Ret.=Proc., m=82026.04 | 27.8 | |
| Template RAG (Self-Discover)Backbone=OpenThinker3-7B, Ret.=Proc., m=82026.04 | 27.6 | |
| Trajectory RAG (Summary)Backbone=Qwen3-32B, Ret.=Proc., m=82026.04 | 26.7 | |
| Document RAG (CompactDS)Backbone=Qwen3-32B, Ret.=Fact., m=82026.04 | 26.7 | |
| Template RAG (ReasonFlux)Backbone=OpenThinker3-7B, Ret.=Proc., m=82026.04 | 26.2 | |
| Length ScalingBackbone=DeepSeek-R1-Distill-Llama-8B, Ret.=N/A, m=82026.04 | 25.5 | |
| Trajectory RAG (Prefix)Backbone=Qwen3-32B, Ret.=Proc., m=82026.04 | 24.9 | |
| Document RAG (Google)Backbone=DeepSeek-R1-Distill-Llama-8B, Ret.=Fact., m=82026.04 | 24.6 | |
| Trajectory RAG (Prefix)Backbone=OpenThinker3-7B, Ret.=Proc., m=82026.04 | 24.2 | |
| Trajectory RAG (Summary)Backbone=OpenThinker3-7B, Ret.=Proc., m=82026.04 | 24.2 | |
| Document RAG (Google)Backbone=OpenThinker3-7B, Ret.=Fact., m=82026.04 | 23.5 | |
| No RAGBackbone=DeepSeek-R1-Distill-Llama-8B, Ret.=N/A, m=82026.04 | 22 | |
| Template RAG (Self-Discover)Backbone=DeepSeek-R1-Distill-Llama-8B, Ret.=Proc., m=82026.04 | 21.3 | |
| Document RAG (CompactDS)Backbone=DeepSeek-R1-Distill-Llama-8B, Ret.=Fact., m=82026.04 | 20.8 | |
| Trajectory RAG (Prefix)Backbone=DeepSeek-R1-Distill-Llama-8B, Ret.=Proc., m=82026.04 | 19.5 | |
| Trajectory RAG (Summary)Backbone=DeepSeek-R1-Distill-Llama-8B, Ret.=Proc., m=82026.04 | 18.4 | |
| Template RAG (ReasonFlux)Backbone=DeepSeek-R1-Distill-Llama-8B, Ret.=Proc., m=82026.04 | 17.4 |