List your company

Mathematical Reasoning on MATH-500 (Avg@4 accuracy)

85Avg@4 AccuracyReQueR
13.44832.02450.669.176Apr 28, 2026

Evaluation results

MethodLinks
ReQueRModel=Qwen3-8B, Temperature=0.62026.0485
CoTModel=Qwen3-8B, Temperature=0.62026.0483.4
ReQueRModel=Qwen2.5-72B-Instruct, Temperature=0.62026.0483
ReQueRModel=Qwen3-1.7B, Temperature=0.62026.0477.6
CoTModel=Qwen2.5-72B-Instruct, Temperature=0.62026.0476.2
ReQueRModel=Llama-3.1-70B-Instruct, Temperature=0.62026.0472
CoTModel=Llama-3.1-70B-Instruct, Temperature=0.62026.0464.6
CoTModel=Qwen3-1.7B, Temperature=0.62026.0464.2
ReQueRModel=Qwen3-0.6B, Temperature=0.62026.0454.4
ReQueRModel=Llama-3.1-8B-Instruct, Temperature=0.62026.0454
ReQueRModel=Llama-3.2-3B-Instruct, Temperature=0.62026.0450.2
CoTModel=Qwen3-0.6B, Temperature=0.62026.0448.8
CoTModel=Llama-3.2-3B-Instruct, Temperature=0.62026.0446.6
CoTModel=Llama-3.1-8B-Instruct, Temperature=0.62026.0445.8
ReQueRModel=Mixtral-8x7B-Instruct, Temperature=0.62026.0433
CoTModel=Mixtral-8x7B-Instruct, Temperature=0.62026.0430.6
ReQueRModel=DS-MoE-16B-Chat, Temperature=0.62026.0419.2
CoTModel=DS-MoE-16B-Chat, Temperature=0.62026.0416.2