KnowU-Bench - Personalized Score (Easy): leaderboard
Partial-credit score for personalized mobile assistance on KnowU-Bench (2026), easy split: 43 vague requests resolved from noisy user logs or by asking an LLM-simulated user, each scored from rule checks fused with a rubric-based judgment of preference alignment. Mean task score in percent; higher is better.
Metric: Average score (%, the 0-1 task score times 100; rule checks fused with a rubric judge) on the 43 easy 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 February 2027. 11 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 78 | #99 |
| 2 | Claude Sonnet 4.6 | 78 | #173 |
| 3 | Qwen 3.5 122B A10B | 69 | #346 |
| 4 | Seed 2.0 Pro | 65 | #222 |
| 5 | Qwen 3.5 397B A17B | 59 | #264 |
| 6 | UI-Venus-1.5-8B | 48 | |
| 7 | Qwen 3 VL 32B | 44 | #622 |
| 8 | GUI-OWL-1.5-8B | 42 | |
| 9 | MAI-UI-8B | 40 | |
| 10 | Qwen 3 VL 8B | 27 | #917 |
| 11 | Qwen 3.5 9B | 17 | #828 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=knowu-bench-personalized-score-easy · How It Works · Data refreshed daily, snapshot 2026-11-21.