List your company

Mathematical Reasoning on DART-Math DM-1

68.4Pass@k AccuracyPOLAR
-2.73615.73234.252.668Jun 4, 2026

Evaluation results

MethodLinks
POLARBackbone=LLaMA-3.2-3B-Instruct, k=52026.0668.4
POLARp@=5, Backbone=Qwen1.5-MoE-A2.7B-Chat2026.0662
POLARp@=4, Backbone=Qwen1.5-MoE-A2.7B-Chat2026.0660.8
FlexiDepthp@=5, Temperature=sampling, Backbone=Qwen2.5-3B-Instruct2026.0660
POLARp@=5, Temperature=sampling, Backbone=Qwen2.5-3B-Instruct2026.0659.8
POLARp@=3, Backbone=Qwen1.5-MoE-A2.7B-Chat2026.0658
POLARp@=4, Temperature=sampling, Backbone=Qwen2.5-3B-Instruct2026.0657.4
FlexiDepthp@=4, Temperature=sampling, Backbone=Qwen2.5-3B-Instruct2026.0655.4
POLARp@=3, Temperature=sampling, Backbone=Qwen2.5-3B-Instruct2026.0654.2
DR.LLMBackbone=LLaMA-3.2-3B-Instruct, k=52026.0653.6
POLARp@=2, Backbone=Qwen1.5-MoE-A2.7B-Chat2026.0653.2
POLARp@=2, Temperature=sampling, Backbone=Qwen2.5-3B-Instruct2026.0650.6
FlexiDepthp@=3, Temperature=sampling, Backbone=Qwen2.5-3B-Instruct2026.0649.6
DR.LLMp@=5, Backbone=Qwen1.5-MoE-A2.7B-Chat2026.0648.4
Base (sampling)Backbone=LLaMA-3.2-3B-Instruct, k=5, Strategy=Stochastic decoding2026.0647.6
POLARBackbone=LLaMA-3.2-3B-Instruct, k=12026.0646.2
DR.LLMp@=3, Backbone=Qwen1.5-MoE-A2.7B-Chat2026.0644.4
DR.LLMp@=4, Backbone=Qwen1.5-MoE-A2.7B-Chat2026.0644.4
POLARp@=1, Temperature=sampling, Backbone=Qwen2.5-3B-Instruct2026.0644.4
DR.LLMp@=2, Backbone=Qwen1.5-MoE-A2.7B-Chat2026.0643.8
POLARp@=1, Backbone=Qwen1.5-MoE-A2.7B-Chat2026.0643.8
FlexiDepthp@=2, Temperature=sampling, Backbone=Qwen2.5-3B-Instruct2026.0643.6
Base (tau=0)Backbone=LLaMA-3.2-3B-Instruct, k=1, Strategy=Greedy decoding2026.0642.4
Base (sampling)p@=5, Temperature=sampling, Backbone=Qwen2.5-3B-Instruct2026.0642.2
Base (sampling)p@=4, Temperature=sampling, Backbone=Qwen2.5-3B-Instruct2026.0640.6
Base (sampling)Backbone=LLaMA-3.2-3B-Instruct, k=1, Strategy=Stochastic decoding2026.0640.6
Base (sampling)p@=5, Backbone=Qwen1.5-MoE-A2.7B-Chat2026.0640
Base (sampling)p@=4, Backbone=Qwen1.5-MoE-A2.7B-Chat2026.0639.6
Base (sampling)p@=3, Backbone=Qwen1.5-MoE-A2.7B-Chat2026.0638.8
Base (τ=0)p@=1, Backbone=Qwen1.5-MoE-A2.7B-Chat2026.0638
DR.LLMp@=1, Backbone=Qwen1.5-MoE-A2.7B-Chat2026.0638
Base (sampling)p@=3, Temperature=sampling, Backbone=Qwen2.5-3B-Instruct2026.0637.8
Base (sampling)p@=2, Backbone=Qwen1.5-MoE-A2.7B-Chat2026.0636.4
Base (sampling)p@=1, Backbone=Qwen1.5-MoE-A2.7B-Chat2026.0635.4
MindSkipBackbone=LLaMA-3.2-3B-Instruct, k=52026.0635.2
Base (sampling)p@=2, Temperature=sampling, Backbone=Qwen2.5-3B-Instruct2026.0632.6
FlexiDepthp@=1, Temperature=sampling, Backbone=Qwen2.5-3B-Instruct2026.0630
FlexiDepthBackbone=LLaMA-3.2-3B-Instruct, k=52026.0628.6
ShortGPTp@=5, Backbone=Qwen1.5-MoE-A2.7B-Chat2026.0627.2
ShortGPTp@=4, Backbone=Qwen1.5-MoE-A2.7B-Chat2026.0626.6
ShortGPTp@=3, Backbone=Qwen1.5-MoE-A2.7B-Chat2026.0625.6
Base (sampling)p@=1, Temperature=sampling, Backbone=Qwen2.5-3B-Instruct2026.0624.2
ShortGPTp@=2, Backbone=Qwen1.5-MoE-A2.7B-Chat2026.0622.4
Base (τ=0)p@=1, Temperature=0, Backbone=Qwen2.5-3B-Instruct2026.0622
DR.LLMp@=5, Temperature=sampling, Backbone=Qwen2.5-3B-Instruct2026.0621.6
DR.LLMp@=4, Temperature=sampling, Backbone=Qwen2.5-3B-Instruct2026.0620.8
ShortGPTp@=1, Backbone=Qwen1.5-MoE-A2.7B-Chat2026.0619.6
DR.LLMp@=3, Temperature=sampling, Backbone=Qwen2.5-3B-Instruct2026.0617.4
ShortGPTBackbone=LLaMA-3.2-3B-Instruct, k=52026.0616.4
DR.LLMp@=2, Temperature=sampling, Backbone=Qwen2.5-3B-Instruct2026.0614.2
DR.LLMp@=1, Temperature=sampling, Backbone=Qwen2.5-3B-Instruct2026.066.8
MindSkipp@=4, Temperature=sampling, Backbone=Qwen2.5-3B-Instruct2026.061.8
MindSkipp@=5, Temperature=sampling, Backbone=Qwen2.5-3B-Instruct2026.061.8
ShortGPTp@=5, Temperature=sampling, Backbone=Qwen2.5-3B-Instruct2026.061.4
MindSkipp@=2, Temperature=sampling, Backbone=Qwen2.5-3B-Instruct2026.061.4
MindSkipp@=3, Temperature=sampling, Backbone=Qwen2.5-3B-Instruct2026.061.4
ShortGPTp@=4, Temperature=sampling, Backbone=Qwen2.5-3B-Instruct2026.061.2
ShortGPTp@=3, Temperature=sampling, Backbone=Qwen2.5-3B-Instruct2026.061
ShortGPTp@=2, Temperature=sampling, Backbone=Qwen2.5-3B-Instruct2026.060.8
MindSkipp@=1, Temperature=sampling, Backbone=Qwen2.5-3B-Instruct2026.060.6
FlexiDepthp@=4, Backbone=Qwen1.5-MoE-A2.7B-Chat2026.060.4
FlexiDepthp@=5, Backbone=Qwen1.5-MoE-A2.7B-Chat2026.060.4
ShortGPTp@=1, Temperature=sampling, Backbone=Qwen2.5-3B-Instruct2026.060.4
MindSkipp@=1, Backbone=Qwen1.5-MoE-A2.7B-Chat2026.060
MindSkipp@=2, Backbone=Qwen1.5-MoE-A2.7B-Chat2026.060
MindSkipp@=3, Backbone=Qwen1.5-MoE-A2.7B-Chat2026.060
MindSkipp@=4, Backbone=Qwen1.5-MoE-A2.7B-Chat2026.060
MindSkipp@=5, Backbone=Qwen1.5-MoE-A2.7B-Chat2026.060
FlexiDepthp@=1, Backbone=Qwen1.5-MoE-A2.7B-Chat2026.060
FlexiDepthp@=2, Backbone=Qwen1.5-MoE-A2.7B-Chat2026.060
FlexiDepthp@=3, Backbone=Qwen1.5-MoE-A2.7B-Chat2026.060