PersTurnBench - Dissatisfaction Rate: leaderboard
Metric: Dissatisfied-turn rate (%): share of replay turns with a calibrated satisfaction of 3 or lower, 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; lower is better. Source: arxiv.org. Saturation forecast: Estimated already saturated. 10 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Kimi K2.6 | 1.3 |
| 2 | DeepSeek V4 Pro | 2.7 |
| 3 | GLM-5.1 | 2.7 |
| 4 | Claude Opus 4.7 | 4.7 |
| 5 | GPT-5.5 | 5.7 |
| 6 | Gemini 3.1 Pro (Preview) | 6 |
| 7 | Qwen 3 8B | 8 |
| 8 | DeepSeek V4 Flash | 10.7 |
| 9 | Gemini 3.1 Flash Lite | 13 |
| 10 | MiniMax-M2.7 | 13.7 |
Interactive version: theaggregate.ai/benchmark?slug=persturnbench-dissatisfaction-rate · How It Works · Data refreshed daily, snapshot 2026-10-07.