List your company

Logical Reasoning on Formal Logic

87.8AccuracyUAB
34.13648.0686275.932Mar 21, 2026Apr 1, 2026Apr 12, 2026Apr 23, 2026May 4, 2026May 15, 2026May 26, 2026

Evaluation results

MethodLinks
UABBackbone Model=GPT-OSS-20B, Budget=N=42026.0587.8
UABBackbone Model=Cohere, Budget=N=42026.0587.3
UniformBackbone Model=GPT-OSS-20B, Budget=N=42026.0586.5
LLM-JudgeBackbone Model=GPT-OSS-20B, Budget=N=42026.0586.5
LLM-JudgeBackbone Model=Cohere, Budget=N=42026.0586.1
UniformBackbone Model=Cohere, Budget=N=42026.0584.3
UABBackbone Model=Gemma3-27B, Budget=N=42026.0584.1
LLM-JudgeBackbone Model=Gemma3-27B, Budget=N=42026.0583.9
UniformBackbone Model=Gemma3-27B, Budget=N=42026.0582.5
N=1Backbone Model=Cohere, Budget=N=12026.0581.4
N=1Backbone Model=Gemma3-27B, Budget=N=12026.0578
OracleModel=Gemma2-9B, Black-Box Friendly=true2026.0477.8
N=1Backbone Model=GPT-OSS-20B, Budget=N=12026.0576.1
OracleModel=Llama3.1-8B, Black-Box Friendly=true2026.0474.1
OracleModel=Qwen2.5-3B, Black-Box Friendly=true2026.0473.5
OracleModel=Llama3.2-3B, Black-Box Friendly=true2026.0471.4
OracleModel=Qwen2.5-7B, Black-Box Friendly=true2026.0467.7
DARModel=Falcon3-7B2026.0360.3
Uncertain PromptBackbone Model=Falcon3-7B, Number of Agents=4, Number of Rounds=22026.0360.3
UABModel=Qwen2.5-7B, N=42026.0559.2
DARBackbone Model=Falcon3-7B, Number of Agents=4, Number of Rounds=22026.0359
MAD-M2Model=Falcon3-7B2026.0358.7
Society Of MindBackbone Model=Falcon3-7B, Number of Agents=4, Number of Rounds=22026.0357.7
Society Of MindModel=Falcon3-7B2026.0357.5
Uncertain PromptModel=Falcon3-7B2026.0357.5
Vote PromptModel=Falcon3-7B2026.0357.5
Vote PromptBackbone Model=Falcon3-7B, Number of Agents=4, Number of Rounds=22026.0357.4
LLM-JudgeModel=Qwen2.5-7B, N=42026.0556.9
UniformModel=Qwen2.5-7B, N=42026.0556.5
RandomModel=Qwen2.5-7B, N=42026.0556.2
N=1Model=Qwen2.5-7B, N=12026.0555.7
MAD-M^2Backbone Model=Falcon3-7B, Number of Agents=4, Number of Rounds=22026.0355.1
LengthModel=Qwen2.5-7B, N=42026.0554
RCSuniModel=Gemma2-9B, Black-Box Friendly=true2026.0452.9
RCSmedoidModel=Gemma2-9B, Black-Box Friendly=true2026.0452.6
Uncertain PromptModel=Llama3.1-8B2026.0352.4
Vote PromptModel=Llama3.1-8B2026.0352.4
GreedyModel=Gemma2-9B, Black-Box Friendly=true2026.0452.4
RCSprobModel=Gemma2-9B, Black-Box Friendly=false2026.0452.4
CEModel=Gemma2-9B, Black-Box Friendly=false2026.0452.1
DARModel=Llama3.1-8B2026.0352
RCSfreqModel=Gemma2-9B, Black-Box Friendly=true2026.0451.8
Vote PromptBackbone Model=Llama3.1-8B, Number of Agents=4, Number of Rounds=22026.0351.6
SCModel=Gemma2-9B, Black-Box Friendly=true2026.0451.6
Society Of MindModel=Llama3.1-8B2026.0350
ANLLModel=Gemma2-9B, Black-Box Friendly=false2026.0450
DARBackbone Model=Llama3.1-8B, Number of Agents=4, Number of Rounds=22026.0349.7
Majority VoteBackbone Model=Falcon3-7B, Number of Agents=4, Number of Rounds=22026.0349.4
RCSmedoidModel=Qwen2.5-7B, Black-Box Friendly=true2026.0449.2
RCSuniModel=Qwen2.5-7B, Black-Box Friendly=true2026.0449.2
RCSprobModel=Qwen2.5-7B, Black-Box Friendly=false2026.0449.2
Uncertain PromptBackbone Model=Llama3.1-8B, Number of Agents=4, Number of Rounds=22026.0348.8
Majority VoteModel=Falcon3-7B2026.0348.7
Society Of MindBackbone Model=Llama3.1-8B, Number of Agents=4, Number of Rounds=22026.0348.7
CEModel=Qwen2.5-7B, Black-Box Friendly=false2026.0448.7
SCModel=Qwen2.5-7B, Black-Box Friendly=true2026.0448.4
NLLModel=Gemma2-9B, Black-Box Friendly=false2026.0448.1
RCSfreqModel=Qwen2.5-7B, Black-Box Friendly=true2026.0447.9
Single-agentModel=Llama3.1-8B2026.0347.2
UABModel=Qwen2.5-1.5B, N=42026.0547.1
LLM-JudgeModel=Qwen2.5-1.5B, N=42026.0545.8
Single-agentBackbone Model=Llama3.1-8B2026.0345.6
Majority VoteBackbone Model=Llama3.1-8B, Number of Agents=4, Number of Rounds=22026.0345.6
Majority VoteModel=Llama3.1-8B2026.0345.5
RCSuniModel=Qwen2.5-3B, Black-Box Friendly=true2026.0444.7
RCSprobModel=Qwen2.5-3B, Black-Box Friendly=false2026.0443.9
RCSmedoidModel=Qwen2.5-3B, Black-Box Friendly=true2026.0443.6
GreedyModel=Qwen2.5-7B, Black-Box Friendly=true2026.0443.6
DARBackbone Model=Qwen2.5-3B, Number of Agents=4, Number of Rounds=22026.0343.4
RCSfreqModel=Qwen2.5-3B, Black-Box Friendly=true2026.0443.4
LengthModel=Qwen2.5-1.5B, N=42026.0543.4
UABModel=Llama3.2-3B, N=42026.0543.4
Uncertain PromptModel=Qwen2.5-3B2026.0342.5
Single-agentBackbone Model=Falcon3-7B2026.0342.5
MAD-M2Model=Qwen2.5-3B2026.0342.3
Majority VoteModel=Qwen2.5-3B2026.0342.3
UniformModel=Qwen2.5-1.5B, N=42026.0542.1
N=1Model=Qwen2.5-1.5B, N=12026.0541.7
CEModel=Qwen2.5-3B, Black-Box Friendly=false2026.0441.3
UniformModel=Llama3.2-3B, N=42026.0541.3
Vote PromptModel=Qwen2.5-3B2026.0340.9
DARModel=Qwen2.5-3B2026.0340.9
Single-agentModel=Falcon3-7B2026.0340.9
RandomModel=Qwen2.5-1.5B, N=42026.0540.9
SCModel=Qwen2.5-3B, Black-Box Friendly=true2026.0440.5
Majority VoteBackbone Model=Qwen2.5-3B, Number of Agents=4, Number of Rounds=22026.0340.1
LengthModel=Llama3.2-3B, N=42026.0539.7
Vote PromptBackbone Model=Qwen2.5-3B, Number of Agents=4, Number of Rounds=22026.0339.4
RCSuniModel=Llama3.1-8B, Black-Box Friendly=true2026.0439.4
Society Of MindModel=Qwen2.5-3B2026.0339.3
MAD-M^2Backbone Model=Llama3.1-8B, Number of Agents=4, Number of Rounds=22026.0339.2
LLM-JudgeModel=Llama3.2-3B, N=42026.0539.2
RandomModel=Llama3.2-3B, N=42026.0538.8
Society Of MindBackbone Model=Qwen2.5-3B, Number of Agents=4, Number of Rounds=22026.0338.6
RCSmedoidModel=Llama3.1-8B, Black-Box Friendly=true2026.0437.8
Vote PromptModel=Qwen2.5-1.5B2026.0337.7
DARModel=Qwen2.5-1.5B2026.0337.3
N=1Model=Llama3.2-3B, N=12026.0537.2
RCSprobModel=Llama3.1-8B, Black-Box Friendly=false2026.0436.8
DARBackbone Model=Qwen2.5-1.5B, Number of Agents=4, Number of Rounds=22026.0336.2