List your company

Mathematical Reasoning on MATH (Score and Strategy Count)

0.863ScorerSIM (Plug-in)
0.250440.409470.56850.72753Dec 9, 2025

Evaluation results

MethodLinks
rSIM (Plug-in)Reasoner=Llama3.3-70B, Planner=3B plug-in2025.120.8634
PromptingReasoner=Llama3.3-70B, Planner=70B2025.120.846
rSIM (Transfer)Reasoner=Llama3.3-70B, Planner=Qwen2.5-1.5B2025.120.8374
rSIM (Plug-in)Reasoner=Llama3.3-70B, Planner=1B plug-in2025.120.8323
PromptingReasoner=Llama3.3-70B, Planner=3B2025.120.7917
PS+Reasoner=Llama3.3-70B, Planner=No2025.120.7830
ZeroCoTReasoner=Llama3.3-70B, Planner=No2025.120.770
rSIMReasoner=Llama3.2-1B, Planner=3B2025.120.6154
rSIMReasoner=Llama3.2-1B, Planner=Qwen2.5-1.5B2025.120.5914
rSIMReasoner=Llama3.2-1B, Planner=1B2025.120.573
PromptingReasoner=Llama3.2-3B, Planner=70B2025.120.5557
ZeroCoTReasoner=Llama3.2-3B, Planner=No2025.120.480
PS+Reasoner=Llama3.2-3B, Planner=No2025.120.4750
PromptingReasoner=Llama3.2-3B, Planner=3B2025.120.4647
PromptingReasoner=Llama3.2-1B, Planner=70B2025.120.3335
ZeroCoTReasoner=Llama3.2-1B, Planner=No2025.120.3060
PS+Reasoner=Llama3.2-1B, Planner=No2025.120.2820
PromptingReasoner=Llama3.2-1B, Planner=3B2025.120.2747