PersTurnBench: 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. The score is user-macro satisfaction on a 1 to 5 scale, averaged within and then across users; 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; higher is better. Source: arxiv.org. Saturation forecast: Estimated already saturated. 10 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Kimi K2.6 | 4.81 | #197 |
| 2 | GLM-5.1 | 4.8 | #200 |
| 3 | DeepSeek V4 Pro | 4.79 | #201 |
| 4 | GPT-5.5 | 4.69 | #56 |
| 5 | Claude Opus 4.7 | 4.64 | #86 |
| 6 | Gemini 3.1 Pro (Preview) | 4.63 | #102 |
| 7 | Qwen 3 8B | 4.47 | #1890 |
| 8 | MiniMax-M2.7 | 4.43 | #539 |
| 9 | DeepSeek V4 Flash | 4.42 | #273 |
| 10 | Gemini 3.1 Flash Lite | 4.34 | #377 |
No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=persturnbench · How It Works · Data refreshed daily, snapshot 2026-11-22.