PersTurnBench (TF-IDF Memory): leaderboard

PersTurnBench (2026) replays turns of real users conversations: the candidate model writes the next assistant reply and a verified personalized evaluator with user memory predicts how satisfied that user would be, calibrated per user. This board gives the candidate model user history retrieved by TF-IDF and reports user-macro satisfaction on a 1 to 5 scale; higher is better.

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: Around February 2027. 3 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1DeepSeek V4 Flash4.42#267
2Qwen 3 8B4.37#1873
3Gemini 3.1 Flash Lite4.29#371

No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=persturnbench-tf-idf-memory · How It Works · Data refreshed daily, snapshot 2026-11-21.