List your company

Theorem-based Reasoning on TheoremQA

53ScorerSIM
4.74417.27229.842.328Dec 9, 2025

Evaluation results

MethodLinks
rSIMReasoner=7B, Planner=7B2025.12535
rSIMReasoner=7B, Planner=0.5B2025.1248.36
PromptingReasoner=14B, Planner=14B2025.1247.45
PromptingReasoner=14B, Planner=7B2025.1243.87
PS+Reasoner=14B, Planner=No2025.1243.40
ZeroCoTReasoner=14B, Planner=No2025.12430
rSIM (Plug-in)Reasoner=Llama3.3-70B, Planner=3B plug-in2025.1241.86
PromptingReasoner=7B, Planner=14B2025.1241.85
rSIM (Transfer)Reasoner=Llama3.3-70B, Planner=Qwen2.5-1.5B2025.1240.76
rSIM (Plug-in)Reasoner=Llama3.3-70B, Planner=1B plug-in2025.12395
rSIMReasoner=0.5B, Planner=7B2025.1238.74
PromptingReasoner=Llama3.3-70B, Planner=70B2025.1238.65
PromptingReasoner=7B, Planner=7B2025.1236.47
ZeroCoTReasoner=7B, Planner=No2025.12360
PSReasoner=7B, Planner=No2025.1234.90
rSIMReasoner=0.5B, Planner=0.5B2025.1234.13
ZeroCoTReasoner=Llama3.3-70B, Planner=No2025.1232.30
PS+Reasoner=Llama3.3-70B, Planner=No2025.12320
PromptingReasoner=Llama3.3-70B, Planner=3B2025.1231.98
rSIMReasoner=Llama3.2-1B, Planner=3B2025.12256
rSIMReasoner=Llama3.2-1B, Planner=Qwen2.5-1.5B2025.1224.25
PromptingReasoner=Llama3.2-3B, Planner=70B2025.1222.86
rSIMReasoner=Llama3.2-1B, Planner=1B2025.1220.93
ZeroCoTReasoner=Llama3.2-3B, Planner=No2025.1220.70
PromptingReasoner=Llama3.2-3B, Planner=3B2025.1219.98
PS+Reasoner=Llama3.2-3B, Planner=No2025.1218.60
PromptingReasoner=Llama3.2-1B, Planner=70B2025.1214.35
ZeroCoTReasoner=Llama3.2-1B, Planner=No2025.1213.70
PS+Reasoner=Llama3.2-1B, Planner=No2025.1212.20
PromptingReasoner=0.5B, Planner=14B2025.12105
PromptingReasoner=0.5B, Planner=7B2025.129.68
ZeroCoTReasoner=0.5B, Planner=No2025.129.50
PS+Reasoner=0.5B, Planner=No2025.1280
PromptingReasoner=Llama3.2-1B, Planner=3B2025.126.66