List your company

Grammar Synthesis on Synthetic Grammar Synthesis

100Accuracy ($a^n b^n c^n$)Llama 1B
2.34427.69753.0578.403Mar 3, 2025

Evaluation results

MethodLinks
Llama 1BAlgorithm=SEM-CTRL2025.03100100100
Llama 8BAlgorithm=SEM-CTRL2025.03100100100
Llama 70BAlgorithm=SEM-CTRL2025.03100100100
o4-miniAlgorithm=API2025.0393.393.3100
DeepSeek-R1Algorithm=API2025.0387.67099.6
o1-previewAlgorithm=API2025.0383.380.698.6
Llama 70BAlgorithm=BoN2025.0378.359.691.1
Llama 8BAlgorithm=BoN2025.0339.333.798.9
Llama 70BAlgorithm=Base2025.03303.177.4
Llama 1BAlgorithm=BoN2025.03165.467.1
Llama 8BAlgorithm=Base2025.037.7042.5
Llama 1BAlgorithm=Base2025.036.12.140.5