Code on LiveCodeBench V5-6
50.8AccuracyReasoning Memory
Evaluation Results
| Method | Links | |
|---|---|---|
| Reasoning MemoryBackbone=Qwen3-32B, Ret.=Proc., m=302026.04 | 50.8 | |
| Reasoning MemoryBackbone=Qwen3-32B, Ret.=Proc., m=82026.04 | 50.3 | |
| Length ScalingBackbone=Qwen3-32B, Ret.=N/A, m=302026.04 | 47.6 | |
| No RAGBackbone=Qwen3-32B, Ret.=N/A, m=82026.04 | 46.5 | |
| Length ScalingBackbone=Qwen3-32B, Ret.=N/A, m=82026.04 | 44.4 | |
| Trajectory RAG (Prefix)Backbone=Qwen3-32B, Ret.=Proc., m=82026.04 | 43.2 | |
| Document RAG (Google)Backbone=Qwen3-32B, Ret.=Fact., m=82026.04 | 42.6 | |
| Trajectory RAG (Summary)Backbone=Qwen3-32B, Ret.=Proc., m=82026.04 | 41.8 | |
| Reasoning MemoryBackbone=OpenThinker3-7B, Ret.=Proc., m=302026.04 | 41.2 | |
| Reasoning MemoryBackbone=OpenThinker3-7B, Ret.=Proc., m=82026.04 | 39.7 | |
| Length ScalingBackbone=OpenThinker3-7B, Ret.=N/A, m=82026.04 | 34.4 | |
| Length ScalingBackbone=OpenThinker3-7B, Ret.=N/A, m=302026.04 | 34.3 | |
| Template RAG (Self-Discover)Backbone=Qwen3-32B, Ret.=Proc., m=82026.04 | 33.9 | |
| Reasoning MemoryBackbone=DeepSeek-R1-Distill-Llama-8B, Ret.=Proc., m=302026.04 | 32.5 | |
| Length ScalingBackbone=DeepSeek-R1-Distill-Llama-8B, Ret.=N/A, m=302026.04 | 30.2 | |
| Reasoning MemoryBackbone=DeepSeek-R1-Distill-Llama-8B, Ret.=Proc., m=82026.04 | 29.2 | |
| Document RAG (CompactDS)Backbone=Qwen3-32B, Ret.=Fact., m=82026.04 | 28.4 | |
| Template RAG (Self-Discover)Backbone=OpenThinker3-7B, Ret.=Proc., m=82026.04 | 27.9 | |
| Length ScalingBackbone=DeepSeek-R1-Distill-Llama-8B, Ret.=N/A, m=82026.04 | 27.8 | |
| Template RAG (ReasonFlux)Backbone=Qwen3-32B, Ret.=Proc., m=82026.04 | 27.8 | |
| Template RAG (ReasonFlux)Backbone=OpenThinker3-7B, Ret.=Proc., m=82026.04 | 26.8 | |
| No RAGBackbone=OpenThinker3-7B, Ret.=N/A, m=82026.04 | 26.6 | |
| Trajectory RAG (Summary)Backbone=OpenThinker3-7B, Ret.=Proc., m=82026.04 | 26 | |
| Document RAG (CompactDS)Backbone=OpenThinker3-7B, Ret.=Fact., m=82026.04 | 25.8 | |
| Trajectory RAG (Prefix)Backbone=OpenThinker3-7B, Ret.=Proc., m=82026.04 | 24.9 | |
| Template RAG (Self-Discover)Backbone=DeepSeek-R1-Distill-Llama-8B, Ret.=Proc., m=82026.04 | 24.7 | |
| Document RAG (Google)Backbone=OpenThinker3-7B, Ret.=Fact., m=82026.04 | 23.1 | |
| Document RAG (Google)Backbone=DeepSeek-R1-Distill-Llama-8B, Ret.=Fact., m=82026.04 | 22.8 | |
| No RAGBackbone=DeepSeek-R1-Distill-Llama-8B, Ret.=N/A, m=82026.04 | 21.1 | |
| Template RAG (ReasonFlux)Backbone=DeepSeek-R1-Distill-Llama-8B, Ret.=Proc., m=82026.04 | 21 | |
| Document RAG (CompactDS)Backbone=DeepSeek-R1-Distill-Llama-8B, Ret.=Fact., m=82026.04 | 17.2 | |
| Trajectory RAG (Prefix)Backbone=DeepSeek-R1-Distill-Llama-8B, Ret.=Proc., m=82026.04 | 12.8 | |
| Trajectory RAG (Summary)Backbone=DeepSeek-R1-Distill-Llama-8B, Ret.=Proc., m=82026.04 | 12.1 |