List your company

Mathematical Reasoning on GSM8K (test) (Exact Match %)

95.83Exact Match Accuracy (GSM8K Test)Top-k
-3.833222.040947.91573.7891Apr 13, 2026

Evaluation results

MethodLinks
Top-kModel=Qwen3-30B-Instruct, Temperature=1.02026.0495.83
Top-nσModel=Qwen3-30B-Instruct, Temperature=1.02026.0495.68
Top-pModel=Qwen3-30B-Instruct, Temperature=1.02026.0495.6
Min-pModel=Qwen3-30B-Instruct, Temperature=1.02026.0495.6
Top-nσModel=Qwen3-30B-Instruct, Temperature=2.02026.0495.6
Min-kModel=Qwen3-30B-Instruct, Temperature=1.02026.0495.6
Min-kModel=Qwen3-30B-Instruct, Temperature=3.02026.0495.6
Top-nσModel=Qwen3-30B-Instruct, Temperature=4.02026.0495.45
Min-kModel=Qwen3-30B-Instruct, Temperature=4.02026.0495.45
Top-nσModel=Qwen3-30B-Instruct, Temperature=3.02026.0495.37
Min-kModel=Qwen3-30B-Instruct, Temperature=5.02026.0495.37
Min-kModel=Qwen3-30B-Instruct, Temperature=10.02026.0495.37
Top-nσModel=Qwen3-30B-Instruct, Temperature=5.02026.0495.3
Top-kModel=Qwen3-30B-Instruct, Temperature=2.02026.0495.15
Min-kModel=Qwen3-30B-Instruct, Temperature=2.02026.0495.07
Top-pModel=Qwen3-30B-Instruct, Temperature=2.02026.0495
Min-pModel=Qwen3-30B-Instruct, Temperature=2.02026.0495
Min-pModel=Qwen3-30B-Instruct, Temperature=3.02026.0494.92
Top-nσModel=Qwen3-30B-Instruct, Temperature=10.02026.0494.69
Top-kModel=Qwen3-30B-Instruct, Temperature=3.02026.0494.62
Top-nσModel=LLaMA3-70B-Instruct, Temperature=3.02026.0494.01
Top-nσModel=LLaMA3-70B-Instruct, Temperature=2.02026.0493.25
Top-pModel=LLaMA3-70B-Instruct, Temperature=1.02026.0492.95
Top-nσModel=LLaMA3-70B-Instruct, Temperature=10.02026.0492.95
Min-kModel=LLaMA3-70B-Instruct, Temperature=1.02026.0492.95
Top-pModel=Qwen3-30B-Instruct, Temperature=3.02026.0492.95
Min-pModel=LLaMA3-70B-Instruct, Temperature=1.02026.0492.87
Top-nσModel=LLaMA3-70B-Instruct, Temperature=1.02026.0492.87
Top-nσModel=LLaMA3-70B-Instruct, Temperature=4.02026.0492.79
Min-kModel=LLaMA3-70B-Instruct, Temperature=3.02026.0492.65
Top-kModel=LLaMA3-70B-Instruct, Temperature=1.02026.0492.64
Min-pModel=Qwen3-30B-Instruct, Temperature=4.02026.0492.57
Top-nσModel=LLaMA3-70B-Instruct, Temperature=5.02026.0492.49
Min-kModel=LLaMA3-70B-Instruct, Temperature=4.02026.0492.42
Min-kModel=LLaMA3-70B-Instruct, Temperature=2.02026.0492.34
Top-pModel=LLaMA3-70B-Instruct, Temperature=2.02026.0492.04
Min-kModel=LLaMA3-70B-Instruct, Temperature=5.02026.0491.96
Min-kModel=LLaMA3-70B-Instruct, Temperature=10.02026.0491.89
Min-pModel=LLaMA3-70B-Instruct, Temperature=2.02026.0491.66
Top-kModel=LLaMA3-70B-Instruct, Temperature=2.02026.0491.13
Top-kModel=Qwen3-30B-Instruct, Temperature=4.02026.0489.46
Min-pModel=LLaMA3-70B-Instruct, Temperature=3.02026.0487.95
Min-pModel=Qwen3-30B-Instruct, Temperature=5.02026.0484.69
Top-kModel=LLaMA3-70B-Instruct, Temperature=3.02026.0481.2
Top-pModel=Qwen3-30B-Instruct, Temperature=4.02026.0477.56
Top-pModel=LLaMA3-70B-Instruct, Temperature=3.02026.0464.22
Top-kModel=Qwen3-30B-Instruct, Temperature=5.02026.0462.02
Min-pModel=LLaMA3-70B-Instruct, Temperature=4.02026.0458.98
Top-pModel=Qwen3-30B-Instruct, Temperature=5.02026.0452.34
Top-kModel=LLaMA3-70B-Instruct, Temperature=4.02026.0436.92
Min-pModel=LLaMA3-70B-Instruct, Temperature=5.02026.0420.77
Top-pModel=LLaMA3-70B-Instruct, Temperature=4.02026.049.63
Top-kModel=LLaMA3-70B-Instruct, Temperature=5.02026.048.57
Top-pModel=LLaMA3-70B-Instruct, Temperature=5.02026.040.83
Min-pModel=Qwen3-30B-Instruct, Temperature=10.02026.040.45
Top-kModel=LLaMA3-70B-Instruct, Temperature=10.02026.040
Top-pModel=LLaMA3-70B-Instruct, Temperature=10.02026.040
Min-pModel=LLaMA3-70B-Instruct, Temperature=10.02026.040
Top-kModel=Qwen3-30B-Instruct, Temperature=10.02026.040
Top-pModel=Qwen3-30B-Instruct, Temperature=10.02026.040