List your company

Mathematical Reasoning on MATH500 (Accuracy and Latency)

81AccuracySPECS
20.78436.41752.0567.683Jun 15, 2025

Evaluation results

MethodLinks
SPECSModel Family=Qwen2.5 Family, n=162025.068115.81.3145.5
SPECSModel Family=Qwen2.5 Family, n=82025.0679.511.31.3145.5
RSD++Model Family=Qwen2.5 Family, n=162025.067916.31.8426.8
RSD++Model Family=Qwen2.5 Family, n=82025.0678.311.81.3728.4
RSD++Model Family=Qwen2.5 Family, n=42025.0677.810.11.1432.3
SPECSModel Family=Qwen2.5 Family, n=42025.06779.831.1149
BS (B)Model Family=Qwen2.5 Family, n=162025.0675.521.32.15100
BS (S)Model Family=Qwen2.5 Family, n=162025.0674.516.81.570
BS (B)Model Family=Qwen2.5 Family, n=82025.0671.313.61.51100
BS (B)Model Family=Qwen2.5 Family, n=42025.0669.311.21.13100
BS (S)Model Family=Qwen2.5 Family, n=82025.0666.710.71.010
BS (S)Model Family=Qwen2.5 Family, n=42025.0664.37.90.650
SPECSModel Family=Llama3 Family, n=162025.064422.90.8678.1
SPECSModel Family=Llama3 Family, n=82025.0640.715.20.5785.2
RSD++Model Family=Llama3 Family, n=162025.0640231.0270.3
RSD++Model Family=Llama3 Family, n=82025.0639.315.20.7173.9
BS (B)Model Family=Llama3 Family, n=162025.063918.90.79100
RSD++Model Family=Llama3 Family, n=42025.0635.711.20.5572.7
SPECSModel Family=Llama3 Family, n=42025.0635.310.80.491.1
BS (S)Model Family=Llama3 Family, n=162025.0634.317.420.780
BS (B)Model Family=Llama3 Family, n=82025.063312.10.52100
BS (B)Model Family=Llama3 Family, n=42025.06328.40.39100
BS (S)Model Family=Llama3 Family, n=82025.0628.39.550.450
BS (S)Model Family=Llama3 Family, n=42025.0623.14.820.270