List your company

Mathematical Reasoning on GSM8K (test) (Hit@1, TOK (x10^3), AC)

82.9Hit@1 AccuracyMASPRM-7B
45.77255.41165.0574.689Oct 28, 2025

Evaluation results

MethodLinks
MASPRM-7BSearch=MCTS(10,3), Agent=Qwen2.5-1.5B-Instruct2025.1082.95.534.4
MASPRM-7BSearch=SBS(5,3), Agent=Qwen2.5-1.5B-Instruct2025.1077.57.950
MASPRM-7BSearch=SBS(5,1), Agent=Qwen2.5-1.5B-Instruct2025.1073.43.220
MASPRM-1.5BSearch=MCTS(10,3), Agent=Qwen2.5-1.5B-Instruct2025.1069.85.634.7
MASPRM-1.5BSearch=SBS(5,3), Agent=Qwen2.5-1.5B-Instruct2025.1069.18.450
MASPRM-7BSearch=SC@5, Agent=Qwen2.5-1.5B-Instruct2025.1067.83.620
ORM-1.5BSearch=MCTS(10,3), Agent=Qwen2.5-1.5B-Instruct2025.1066.85.835.2
ORM-1.5BSearch=SC@5, Agent=Qwen2.5-1.5B-Instruct2025.1065.43.620
MASPRM-1.5BSearch=SC@5, Agent=Qwen2.5-1.5B-Instruct2025.1064.23.620
Qwen2.5-1.5B-InstructSearch=SC@5, Scorer=None2025.1063.43.620
MASPRM-1.5BSearch=SBS(5,1), Agent=Qwen2.5-1.5B-Instruct2025.1063.43.420
Qwen2.5-1.5B-InstructSearch=MCTS(10,3), Scorer=Policy Likelihood2025.1062.55.738.2
Qwen2.5-1.5B-InstructSearch=SC@5, Scorer=Policy Likelihood2025.1061.23.620
Qwen2.5-1.5B-InstructSearch=SBS(5,3), Scorer=Policy Likelihood2025.1060.38.450
Qwen2.5-1.5B-InstructSearch=SBS(5,1), Scorer=Policy Likelihood2025.10553.620
Qwen2.5-1.5B-InstructSearch=Single-Pass, Scorer=None2025.1047.20.74