KnowU-Bench - Proactive (Hard): leaderboard

Proactive mobile assistance on KnowU-Bench (2026), hard split: 32 situations at the higher of the two difficulty levels with no instruction, where the agent must decide whether to act, seek consent or stay silent and must respect a rejection by the simulated user. Success rate in percent; higher is better.

Metric: Success rate (%) on the 32 hard proactive tasks (no instruction: act, ask for consent or stay silent, and respect a rejection) 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 2029. 10 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1Qwen 3.5 9B65.6#828
2Seed 2.0 Pro62.5#222
3Qwen 3.5 397B A17B56.3#264
4Claude Sonnet 4.653.1#173
5Qwen 3 VL 32B34.4#622
6UI-Venus-1.5-8B31.3
7MAI-UI-8B22.2
8Qwen 3 VL 8B21.9#917
9GUI-OWL-1.5-8B21.9
10Qwen 3.5 122B A10B12.5#346

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-proactive-hard · How It Works · Data refreshed daily, snapshot 2026-11-21.