List your company

Mathematical Reasoning on AMC 2025 (test)

76.31Acc@5LARK
7.805225.590143.37561.1599May 28, 2026

Evaluation results

MethodLinks
LARKBackbone=Qwen-2.5-7B, Selection Budget (B)=32026.0576.31
Rule-based QualitymaxBackbone=Qwen-2.5-7B, Selection Budget (B)=32026.0567.07
RSRminBackbone=Qwen-2.5-7B, Selection Budget (B)=32026.0566.27
LARKBackbone=Qwen-2.5-7B, Selection Budget (B)=12026.0565.86
Local NaturalnessmaxBackbone=Qwen-2.5-7B, Selection Budget (B)=32026.0564.26
GRAPEmaxBackbone=Qwen-2.5-7B, Selection Budget (B)=32026.0563.05
LLM-judged QualitymaxBackbone=Qwen-2.5-7B, Selection Budget (B)=32026.0562.25
RandomBackbone=Qwen-2.5-7B, Selection Budget (B)=32026.0561.45
RSRminBackbone=Qwen-2.5-7B, Selection Budget (B)=12026.0559.44
Local NaturalnessmaxBackbone=Qwen-2.5-7B, Selection Budget (B)=12026.0557.83
Token LengthmaxBackbone=Qwen-2.5-7B, Selection Budget (B)=32026.0557.03
Rule-based QualitymaxBackbone=Qwen-2.5-7B, Selection Budget (B)=12026.0556.63
LLM-judged QualitymaxBackbone=Qwen-2.5-7B, Selection Budget (B)=12026.0556.22
GRAPEmaxBackbone=Qwen-2.5-7B, Selection Budget (B)=12026.0555.02
RandomBackbone=Qwen-2.5-7B, Selection Budget (B)=12026.0551
Token LengthmaxBackbone=Qwen-2.5-7B, Selection Budget (B)=12026.0550.6
BaseModelBackbone=Qwen-2.5-7B, Selection Budget (B)=12026.0547.79
BaseModelBackbone=Qwen-2.5-7B, Selection Budget (B)=32026.0547.79
LARKBackbone=Qwen-2.5-1.5B, Selection Budget (B)=32026.0542.57
LARKBackbone=Qwen-2.5-1.5B, Selection Budget (B)=12026.0540.56
Local NaturalnessmaxBackbone=Qwen-2.5-1.5B, Selection Budget (B)=32026.0538.96
Rule-based QualitymaxBackbone=Qwen-2.5-1.5B, Selection Budget (B)=32026.0538.55
GRAPEmaxBackbone=Qwen-2.5-1.5B, Selection Budget (B)=32026.0538.15
Local NaturalnessmaxBackbone=Qwen-2.5-1.5B, Selection Budget (B)=12026.0536.14
RSRminBackbone=Qwen-2.5-1.5B, Selection Budget (B)=32026.0536.14
GRAPEmaxBackbone=Qwen-2.5-1.5B, Selection Budget (B)=12026.0535.34
LLM-judged QualitymaxBackbone=Qwen-2.5-1.5B, Selection Budget (B)=32026.0535.34
RandomBackbone=Qwen-2.5-1.5B, Selection Budget (B)=12026.0533.33
RandomBackbone=Qwen-2.5-1.5B, Selection Budget (B)=32026.0532.93
RSRminBackbone=Qwen-2.5-1.5B, Selection Budget (B)=12026.0532.13
Rule-based QualitymaxBackbone=Qwen-2.5-1.5B, Selection Budget (B)=12026.0529.72
LLM-judged QualitymaxBackbone=Qwen-2.5-1.5B, Selection Budget (B)=12026.0529.32
Token LengthmaxBackbone=Qwen-2.5-1.5B, Selection Budget (B)=32026.0525.7
Token LengthmaxBackbone=Qwen-2.5-1.5B, Selection Budget (B)=12026.0525.3
BaseModelBackbone=Qwen-2.5-1.5B, Selection Budget (B)=12026.0524.5
BaseModelBackbone=Qwen-2.5-1.5B, Selection Budget (B)=32026.0524.5
LARKBackbone=Llama-3.2-3B, Selection Budget (B)=32026.0522.09
GRAPEmaxBackbone=Llama-3.2-3B, Selection Budget (B)=32026.0520.48
Local NaturalnessmaxBackbone=Llama-3.2-3B, Selection Budget (B)=32026.0520.08
LARKBackbone=Llama-3.2-3B, Selection Budget (B)=12026.0519.28
LLM-judged QualitymaxBackbone=Llama-3.2-3B, Selection Budget (B)=12026.0518.88
LLM-judged QualitymaxBackbone=Llama-3.2-3B, Selection Budget (B)=32026.0518.47
Local NaturalnessmaxBackbone=Llama-3.2-3B, Selection Budget (B)=12026.0517.67
RandomBackbone=Llama-3.2-3B, Selection Budget (B)=32026.0517.67
RSRminBackbone=Llama-3.2-3B, Selection Budget (B)=32026.0517.27
Token LengthmaxBackbone=Llama-3.2-3B, Selection Budget (B)=12026.0516.47
Token LengthmaxBackbone=Llama-3.2-3B, Selection Budget (B)=32026.0516.06
RSRminBackbone=Llama-3.2-3B, Selection Budget (B)=12026.0515.66
Rule-based QualitymaxBackbone=Llama-3.2-3B, Selection Budget (B)=32026.0515.66
RandomBackbone=Llama-3.2-3B, Selection Budget (B)=12026.0514.86
GRAPEmaxBackbone=Llama-3.2-3B, Selection Budget (B)=12026.0514.46
BaseModelBackbone=Llama-3.2-3B, Selection Budget (B)=12026.0511.24
BaseModelBackbone=Llama-3.2-3B, Selection Budget (B)=32026.0511.24
Rule-based QualitymaxBackbone=Llama-3.2-3B, Selection Budget (B)=12026.0510.44