List your company

Text Generation on XSum

25.76F1 ScorePrompt-R1
-0.8126.086512.98519.8835Nov 2, 2025

Evaluation results

MethodLinks
Prompt-R12025.1125.7663.02
TextGradCategory=APO (GPT-4o-mini)2025.1124.8828.45
BaselineBackbone=GPT-4o-mini2025.1124.3560.56
GRPOBackbone=Qwen3-4B2025.1121.9852.09
SFTBackbone=Qwen3-4B2025.1121.1355.65
OPROCategory=APO (GPT-4o-mini)2025.1117.8729.47
BaselineBackbone=Qwen3-4B2025.1116.7531.73
CoT ReasoningBackbone=GPT-4o-mini2025.118.9253.94
CoT ReasoningBackbone=Qwen3-4B2025.118.336.81
GEPACategory=APO (GPT-4o-mini)2025.110.210.37