List your company
ResearchFormerly WizWand

Mathematical Reasoning on Minerva Math (Avg@16 Accuracy)

39Accuracy (Avg@16)PROF-BOTH
7.59215.74623.932.054Sep 3, 2025
Updated 5mo ago

Evaluation results

MethodLinks
PROF-BOTHModel=Qwen2.5-Math-7B-base, Temperature=1.0, Evaluation Protocol=average@162025.0939
GRPOModel=Qwen2.5-Math-7B-base, Temperature=1.0, Evaluation Protocol=average@162025.0937.2
BlendModel=Qwen2.5-Math-7B-base, Temperature=1.0, Evaluation Protocol=average@162025.0936.7
PROF-POSModel=Qwen2.5-Math-7B-base, Temperature=1.0, Evaluation Protocol=average@162025.0936.6
PROF-POSModel=Qwen2.5-Math-1.5B-base, Temperature=1.0, Evaluation Protocol=average@162025.0931.3
PROF-BOTHModel=Qwen2.5-Math-1.5B-base, Temperature=1.0, Evaluation Protocol=average@162025.0930
GRPOModel=Qwen2.5-Math-1.5B-base, Temperature=1.0, Evaluation Protocol=average@162025.0929.1
BlendModel=Qwen2.5-Math-1.5B-base, Temperature=1.0, Evaluation Protocol=average@162025.0927.8
PROF-POSModel=LLaMA-3.2-3B-instruct, Temperature=1.0, Evaluation Protocol=average@162025.0919.5
GRPOModel=LLaMA-3.2-3B-instruct, Temperature=1.0, Evaluation Protocol=average@162025.0918.8
PROF-BOTHModel=LLaMA-3.2-3B-instruct, Temperature=1.0, Evaluation Protocol=average@162025.0918
BlendModel=LLaMA-3.2-3B-instruct, Temperature=1.0, Evaluation Protocol=average@162025.0913.1
BaseModel=Qwen2.5-Math-7B-base, Temperature=1.0, Evaluation Protocol=average@162025.0912.8
BaseModel=Qwen2.5-Math-1.5B-base, Temperature=1.0, Evaluation Protocol=average@162025.0911.4
BaseModel=LLaMA-3.2-3B-instruct, Temperature=1.0, Evaluation Protocol=average@162025.098.8