SePO: Self-Evolving Prompt Agent for System Prompt Optimization
Open paper
Benchmark
Model
Rank
Results
code-generation-on-mbpp
SePO-Generalist
–
Accuracy: 96.2
mathematical-reasoning-on-aime-2025
SePO-Generalist
–
Accuracy: 64.22
Rank counts only results with a code link.