KnowU-Bench - General (Easy): leaderboard

Explicit-instruction GUI execution on KnowU-Bench (2026), easy general split: 18 tasks with fully specified instructions in a live Android emulator, the baseline for the personalized and proactive splits. Success rate in percent; higher is better.

Metric: Success rate (%) on the 18 easy general tasks (explicit instructions) 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: Estimated already saturated. 11 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1Seed 2.0 Pro100#222
2MAI-UI-8B100
3Gemini 3.1 Pro (Preview)94.4#99
4Claude Sonnet 4.694.4#173
5Qwen 3.5 122B A10B94.4#346
6Qwen 3.5 9B83.3#828
7Qwen 3.5 397B A17B83.3#264
8Qwen 3 VL 32B77.8#622
9GUI-OWL-1.5-8B77.8
10Qwen 3 VL 8B72.2#917
11UI-Venus-1.5-8B72.2

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-general-easy · How It Works · Data refreshed daily, snapshot 2026-11-21.