List your company
ResearchFormerly WizWand

Mathematical Reasoning on Math500 (average@16 accuracy)

83.1Average Accuracy @16PROF-BOTH
27.87642.21356.5570.887Sep 3, 2025
Updated 5mo ago

Evaluation results

MethodLinks
PROF-BOTHModel=Qwen2.5-Math-7B-base, Temperature=1.0, Evaluation Protocol=average@162025.0983.1
BlendModel=Qwen2.5-Math-7B-base, Temperature=1.0, Evaluation Protocol=average@162025.0981.7
GRPOModel=Qwen2.5-Math-7B-base, Temperature=1.0, Evaluation Protocol=average@162025.0981.6
PROF-POSModel=Qwen2.5-Math-7B-base, Temperature=1.0, Evaluation Protocol=average@162025.0981.4
PROF-BOTHModel=Qwen2.5-Math-1.5B-base, Temperature=1.0, Evaluation Protocol=average@162025.0973.2
PROF-POSModel=Qwen2.5-Math-1.5B-base, Temperature=1.0, Evaluation Protocol=average@162025.0972.6
GRPOModel=Qwen2.5-Math-1.5B-base, Temperature=1.0, Evaluation Protocol=average@162025.0970.3
BlendModel=Qwen2.5-Math-1.5B-base, Temperature=1.0, Evaluation Protocol=average@162025.0967.6
PROF-POSModel=LLaMA-3.2-3B-instruct, Temperature=1.0, Evaluation Protocol=average@162025.0952.4
GRPOModel=LLaMA-3.2-3B-instruct, Temperature=1.0, Evaluation Protocol=average@162025.0950.5
PROF-BOTHModel=LLaMA-3.2-3B-instruct, Temperature=1.0, Evaluation Protocol=average@162025.0949
BaseModel=Qwen2.5-Math-7B-base, Temperature=1.0, Evaluation Protocol=average@162025.0942
BaseModel=Qwen2.5-Math-1.5B-base, Temperature=1.0, Evaluation Protocol=average@162025.0939.9
BlendModel=LLaMA-3.2-3B-instruct, Temperature=1.0, Evaluation Protocol=average@162025.0937.2
BaseModel=LLaMA-3.2-3B-instruct, Temperature=1.0, Evaluation Protocol=average@162025.0930