List your company

Mathematical Reasoning on OlympiadBench (Accuracy, Latency, % B)

0.44AccuracySPECS
0.058320.157410.25650.35559Jun 15, 2025

Evaluation results

MethodLinks
SPECSModel Family=Qwen2.5 Family, n=162025.060.4424.62.560.615
BS (B)Model Family=Qwen2.5 Family, n=162025.060.43725.42.571
SPECSModel Family=Qwen2.5 Family, n=82025.060.41716.91.80.803
SPECSModel Family=Qwen2.5 Family, n=42025.060.41313.11.30.831
BS (B)Model Family=Qwen2.5 Family, n=82025.060.41317.91.811
BS (B)Model Family=Qwen2.5 Family, n=42025.060.39313.11.321
RSD++Model Family=Qwen2.5 Family, n=162025.060.33528.72.580.612
RSD++Model Family=Qwen2.5 Family, n=82025.060.33321.71.960.653
RSD++Model Family=Qwen2.5 Family, n=42025.060.3317.31.60.663
BS (S)Model Family=Qwen2.5 Family, n=162025.060.31321.12.020
BS (S)Model Family=Qwen2.5 Family, n=82025.060.3113.41.220
BS (S)Model Family=Qwen2.5 Family, n=42025.060.257.90.810
BS (B)Model Family=Llama3 Family, n=162025.060.2230.11.21
SPECSModel Family=Llama3 Family, n=162025.060.231.71.210.911
SPECSModel Family=Llama3 Family, n=82025.060.18519.70.780.946
BS (B)Model Family=Llama3 Family, n=82025.060.18318.90.831
SPECSModel Family=Llama3 Family, n=42025.060.1814.90.620.981
BS (B)Model Family=Llama3 Family, n=42025.060.17130.591
BS (S)Model Family=Llama3 Family, n=162025.060.11323.171.060
RSD++Model Family=Llama3 Family, n=162025.060.09525.81.180.932
BS (S)Model Family=Llama3 Family, n=42025.060.085.580.350
BS (S)Model Family=Llama3 Family, n=82025.060.0811.090.590
RSD++Model Family=Llama3 Family, n=82025.060.0818.90.830.929
RSD++Model Family=Llama3 Family, n=42025.060.07313.10.610.952