PersTurnBench (TF-IDF Memory): leaderboard
Metric: User-macro satisfaction (1-5): calibrated predicted satisfaction averaged within each user and then across users, PersTurnBench replay of 300 turns from 90 users (180 user-task blocks): the candidate fills only the current assistant turn and the frozen Qwen3-8B memory evaluator predicts the user's turn satisfaction, reference-CDF calibrated per user, the candidate generator also given user history retrieved by TF-IDF; higher is better. Source: arxiv.org. Saturation forecast: Estimated already saturated. 3 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | DeepSeek V4 Flash | 4.42 |
| 2 | Qwen 3 8B | 4.37 |
| 3 | Gemini 3.1 Flash Lite | 4.29 |
Interactive version: theaggregate.ai/benchmark?slug=persturnbench-tf-idf-memory · How It Works · Data refreshed daily, snapshot 2026-10-07.