Personalized Turn-Level User Conversation Sati: leaderboard
User satisfaction with AI assistants is highly personalized: the same response may satisfy one user but disappoint another depending on what each user expects and what they have asked for before. Existing automatic evaluation methods mostly measure generic response quality, making it difficult to judge whether a response satisfies a user at a specific turn. We study this problem as personalized tu
Metric: Micro (self-reported). Source: benchmarklist.com. Saturation forecast: Around August 2027. 7 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Kimi K2.6 | 4.74 | #104 |
| 2 | GLM-5.1 | 4.71 | #97 |
| 3 | DeepSeek V4 Pro | 4.67 | #102 |
| 4 | GPT-5.5 | 4.57 | #31 |
| 5 | Claude Opus 4.7 | 4.54 | #49 |
| 6 | Gemini 3.1 Pro (Preview) | 4.53 | #58 |
| 7 | MiniMax-M2.7 | 4.26 | #258 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=personalized-turn-level-user-conversation-sati · How It Works · Data refreshed daily, snapshot 2026-10-20.