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

#ModelScoreOverall rank
1Gemini 3.1 Pro (Preview)78#99
2Claude Sonnet 4.678#173
3Qwen 3.5 122B A10B69#346
4Seed 2.0 Pro65#222
5Qwen 3.5 397B A17B59#264
6UI-Venus-1.5-8B48
7Qwen 3 VL 32B44#622
8GUI-OWL-1.5-8B42
9MAI-UI-8B40
10Qwen 3 VL 8B27#917
11Qwen 3.5 9B17#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.