SocialPersona - Dialogue (Hierarchical Profile): leaderboard

Metric: Dialogue score (0 to 5): GPT-5.5 judge mean of interest coverage, concreteness and fluency of responses to stable-interest recommendation and recent-interest exploration requests, judged against the gold profile; the response is written from a profile the model first built by summarizing 20-post chunks; higher is better. Source: arxiv.org. Saturation forecast: Around January 2028. 6 models tracked.

Top models

#ModelScore
1GPT-5.43.48
2Qwen 3 VL 8B Instruct3.1
3GPT-4o Mini3.06
4Qwen 3.5 35B A3B2.92
5Qwen 2.5 VL 7B Instruct2.68
6Gemini 2.5 Flash2.57

Interactive version: theaggregate.ai/benchmark?slug=socialpersona-dialogue-hierarchical-profile · How It Works · Data refreshed daily, snapshot 2026-09-29.