Psi-Bench - Everyday Request Personalization: leaderboard
Metric: Personalized response score (how well responses are tailored to the hidden client profile), everyday requests (1-9; DeepSeek-v3.2 judge, which also plays the persona-profiled client; three rounds after the client's opening message, client profile hidden from the model). Source: arxiv.org. Saturation forecast: Around 2028. 10 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.1 | 6.12 |
| 2 | Qwen 3 Next 80B A3B | 5.77 |
| 3 | DeepSeek V4 Pro | 5.15 |
| 4 | Gemini 3.1 Pro (Preview) | 5.14 |
| 5 | Gemini 3 Flash | 5.1 |
| 6 | Qwen 3 32B | 4.66 |
| 7 | GPT-5 Mini | 4.42 |
| 8 | Grok 4 Fast | 4.34 |
| 9 | DeepSeek V3.2 | 4.32 |
| 10 | Qwen 3 8B | 3.63 |
Interactive version: theaggregate.ai/benchmark?slug=psi-bench-everyday-request-personalization · How It Works · Data refreshed daily, snapshot 2026-09-29.