PersTurnBench: 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; higher is better. Source: arxiv.org. Saturation forecast: Estimated already saturated. 10 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Kimi K2.6 | 4.81 |
| 2 | GLM-5.1 | 4.8 |
| 3 | DeepSeek V4 Pro | 4.79 |
| 4 | GPT-5.5 | 4.69 |
| 5 | Claude Opus 4.7 | 4.64 |
| 6 | Gemini 3.1 Pro (Preview) | 4.63 |
| 7 | Qwen 3 8B | 4.47 |
| 8 | MiniMax-M2.7 | 4.43 |
| 9 | DeepSeek V4 Flash | 4.42 |
| 10 | Gemini 3.1 Flash Lite | 4.34 |
Interactive version: theaggregate.ai/benchmark?slug=persturnbench · How It Works · Data refreshed daily, snapshot 2026-10-07.