List your company

Mathematical Reasoning on AIME (Throughput and Efficiency Metrics)

61.79ThroughputSTAND
15.998827.886939.77551.6631Jun 5, 2025

Evaluation results

MethodLinks
STANDBackbone Model=DeepSeek-R1-Distill-Qwen-7B, Evaluation Pattern=Single-trajectory2025.0661.792.323.07
SAM+RecycleBackbone Model=DeepSeek-R1-Distill-Qwen-7B, Evaluation Pattern=Single-trajectory2025.0661.152.32.7
RecycleBackbone Model=DeepSeek-R1-Distill-Qwen-7B, Evaluation Pattern=Single-trajectory2025.0660.612.282.73
ANPDBackbone Model=DeepSeek-R1-Distill-Qwen-7B, Evaluation Pattern=Single-trajectory2025.0646.181.731.88
PLDBackbone Model=DeepSeek-R1-Distill-Qwen-7B, Evaluation Pattern=Single-trajectory2025.0644.341.671.72
SAMBackbone Model=DeepSeek-R1-Distill-Qwen-7B, Evaluation Pattern=Single-trajectory2025.0640.851.531.69
STANDBackbone Model=DeepSeek-R1-Distill-Qwen-14B, Evaluation Pattern=Single-trajectory2025.0634.521.942.91
SAM+RecycleBackbone Model=DeepSeek-R1-Distill-Qwen-14B, Evaluation Pattern=Single-trajectory2025.0634.351.932.67
RecycleBackbone Model=DeepSeek-R1-Distill-Qwen-14B, Evaluation Pattern=Single-trajectory2025.0633.711.92.77
Eagle-2Backbone Model=DeepSeek-R1-Distill-Qwen-7B, Evaluation Pattern=Single-trajectory2025.0629.911.122.21
PlainBackbone Model=DeepSeek-R1-Distill-Qwen-7B, Evaluation Pattern=Single-trajectory2025.0626.63——
ANPDBackbone Model=DeepSeek-R1-Distill-Qwen-14B, Evaluation Pattern=Single-trajectory2025.0625.61.441.76
Eagle-2Backbone Model=DeepSeek-R1-Distill-Qwen-14B, Evaluation Pattern=Single-trajectory2025.0625.381.432.72
SAMBackbone Model=DeepSeek-R1-Distill-Qwen-14B, Evaluation Pattern=Single-trajectory2025.0623.261.311.63
PLDBackbone Model=DeepSeek-R1-Distill-Qwen-14B, Evaluation Pattern=Single-trajectory2025.0621.821.231.61
PlainBackbone Model=DeepSeek-R1-Distill-Qwen-14B, Evaluation Pattern=Single-trajectory2025.0617.76——