List your company

Mathematical Reasoning on DART-Math DM-3

46Pass@k AccuracyPOLAR
-1.8410.582335.42Jun 4, 2026

Evaluation results

MethodLinks
POLARBackbone=LLaMA-3.2-3B-Instruct, k=52026.0646
POLARp@=5, Backbone=Qwen1.5-MoE-A2.7B-Chat2026.0633
Base (sampling)Backbone=LLaMA-3.2-3B-Instruct, k=52026.0632.8
POLARp@=4, Backbone=Qwen1.5-MoE-A2.7B-Chat2026.0631.2
POLARp@=3, Backbone=Qwen1.5-MoE-A2.7B-Chat2026.0629
POLARp@=2, Backbone=Qwen1.5-MoE-A2.7B-Chat2026.0628.2
POLARp@=5, Temperature=sampling, Backbone=Qwen2.5-3B-Instruct2026.0628.2
DR.LLMp@=5, Backbone=Qwen1.5-MoE-A2.7B-Chat2026.0627.4
POLARp@=4, Temperature=sampling, Backbone=Qwen2.5-3B-Instruct2026.0626.8
POLARp@=3, Temperature=sampling, Backbone=Qwen2.5-3B-Instruct2026.0625
DR.LLMp@=4, Backbone=Qwen1.5-MoE-A2.7B-Chat2026.0623.8
DR.LLMp@=3, Backbone=Qwen1.5-MoE-A2.7B-Chat2026.0623.4
DR.LLMp@=2, Backbone=Qwen1.5-MoE-A2.7B-Chat2026.0623.2
POLARp@=2, Temperature=sampling, Backbone=Qwen2.5-3B-Instruct2026.0622.2
POLARp@=1, Backbone=Qwen1.5-MoE-A2.7B-Chat2026.0622
Base (τ=0)p@=1, Backbone=Qwen1.5-MoE-A2.7B-Chat2026.0620.6
DR.LLMp@=1, Backbone=Qwen1.5-MoE-A2.7B-Chat2026.0620.6
Base (sampling)p@=5, Temperature=sampling, Backbone=Qwen2.5-3B-Instruct2026.0620.4
POLARp@=1, Temperature=sampling, Backbone=Qwen2.5-3B-Instruct2026.0620.2
Base (sampling)p@=4, Temperature=sampling, Backbone=Qwen2.5-3B-Instruct2026.0619.2
Base (sampling)p@=5, Backbone=Qwen1.5-MoE-A2.7B-Chat2026.0618.6
Base (sampling)p@=3, Temperature=sampling, Backbone=Qwen2.5-3B-Instruct2026.0618.2
Base (sampling)p@=4, Backbone=Qwen1.5-MoE-A2.7B-Chat2026.0617.8
Base (sampling)p@=3, Backbone=Qwen1.5-MoE-A2.7B-Chat2026.0616.6
Base (sampling)p@=2, Temperature=sampling, Backbone=Qwen2.5-3B-Instruct2026.0616
Base (sampling)p@=2, Backbone=Qwen1.5-MoE-A2.7B-Chat2026.0615.8
Base (sampling)p@=1, Backbone=Qwen1.5-MoE-A2.7B-Chat2026.0614.6
DR.LLMp@=5, Temperature=sampling, Backbone=Qwen2.5-3B-Instruct2026.0612.6
ShortGPTp@=5, Backbone=Qwen1.5-MoE-A2.7B-Chat2026.0612.4
FlexiDepthp@=5, Temperature=sampling, Backbone=Qwen2.5-3B-Instruct2026.0612
Base (sampling)p@=1, Temperature=sampling, Backbone=Qwen2.5-3B-Instruct2026.0611.6
ShortGPTp@=4, Backbone=Qwen1.5-MoE-A2.7B-Chat2026.0611.4
DR.LLMp@=4, Temperature=sampling, Backbone=Qwen2.5-3B-Instruct2026.0611.2
Base (τ=0)p@=1, Temperature=0, Backbone=Qwen2.5-3B-Instruct2026.0611
FlexiDepthp@=4, Temperature=sampling, Backbone=Qwen2.5-3B-Instruct2026.0611
ShortGPTp@=3, Backbone=Qwen1.5-MoE-A2.7B-Chat2026.0610.6
DR.LLMp@=3, Temperature=sampling, Backbone=Qwen2.5-3B-Instruct2026.069.6
ShortGPTp@=2, Backbone=Qwen1.5-MoE-A2.7B-Chat2026.069.4
FlexiDepthp@=3, Temperature=sampling, Backbone=Qwen2.5-3B-Instruct2026.068.6
DR.LLMp@=2, Temperature=sampling, Backbone=Qwen2.5-3B-Instruct2026.067.8
ShortGPTp@=1, Backbone=Qwen1.5-MoE-A2.7B-Chat2026.067.2
FlexiDepthp@=2, Temperature=sampling, Backbone=Qwen2.5-3B-Instruct2026.066.4
DR.LLMp@=1, Temperature=sampling, Backbone=Qwen2.5-3B-Instruct2026.064.6
FlexiDepthp@=1, Temperature=sampling, Backbone=Qwen2.5-3B-Instruct2026.063.2
FlexiDepthp@=2, Backbone=Qwen1.5-MoE-A2.7B-Chat2026.060.2
FlexiDepthp@=3, Backbone=Qwen1.5-MoE-A2.7B-Chat2026.060.2
FlexiDepthp@=4, Backbone=Qwen1.5-MoE-A2.7B-Chat2026.060.2
FlexiDepthp@=5, Backbone=Qwen1.5-MoE-A2.7B-Chat2026.060.2
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
ShortGPTp@=1, Temperature=sampling, Backbone=Qwen2.5-3B-Instruct2026.060
ShortGPTp@=2, Temperature=sampling, Backbone=Qwen2.5-3B-Instruct2026.060
ShortGPTp@=3, Temperature=sampling, Backbone=Qwen2.5-3B-Instruct2026.060
ShortGPTp@=4, Temperature=sampling, Backbone=Qwen2.5-3B-Instruct2026.060
ShortGPTp@=5, Temperature=sampling, Backbone=Qwen2.5-3B-Instruct2026.060
MindSkipp@=1, Temperature=sampling, Backbone=Qwen2.5-3B-Instruct2026.060
MindSkipp@=2, Temperature=sampling, Backbone=Qwen2.5-3B-Instruct2026.060
MindSkipp@=3, Temperature=sampling, Backbone=Qwen2.5-3B-Instruct2026.060
MindSkipp@=4, Temperature=sampling, Backbone=Qwen2.5-3B-Instruct2026.060
MindSkipp@=5, Temperature=sampling, Backbone=Qwen2.5-3B-Instruct2026.060