KnowU-Bench - Personalized Score (Hard): leaderboard
Metric: Average score (%, the 0-1 task score times 100; rule checks fused with a rubric judge) on the 43 hard personalized tasks in the reproducible KnowU-Bench Android emulator, noisy full-history memory setting (the complete user logs plus irrelevant history), gpt-4o as the user simulator grounded in a hidden user profile, scored by rule-based checks fused with a rubric-conditioned LLM judge; higher is better. Source: arxiv.org. Saturation forecast: Around January 2027. 11 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Sonnet 4.6 | 80 |
| 2 | Gemini 3.1 Pro (Preview) | 75 |
| 3 | Qwen 3.5 122B A10B | 60 |
| 4 | Seed 2.0 Pro | 57 |
| 5 | Qwen 3.5 397B A17B | 48 |
| 6 | MAI-UI-8B | 31 |
| 7 | Qwen 3.5 9B | 18 |
Interactive version: theaggregate.ai/benchmark?slug=knowu-bench-personalized-score-hard · How It Works · Data refreshed daily, snapshot 2026-10-07.