List your company

Personalized Interaction on MBPP Synthetic

7.9Personalization ScorePPOpt
5.88246.40626.937.4538Feb 12, 2026

Evaluation results

MethodLinks
PPOptBackbone=Llama-3-8b-instruct2026.027.98.7
PPOptBackbone=GPT-oss-20b2026.027.788.86
PPOptBackbone=Qwen3-8b2026.027.748.84
VanillaBackbone=Llama-3-8b-instruct2026.025.969.08
VanillaBackbone=Qwen3-8b2026.025.969.08
VanillaBackbone=GPT-oss-20b2026.025.969.08