KnowU-Bench - General (Hard): leaderboard

Explicit-instruction GUI execution on KnowU-Bench (2026), hard general split: 24 tasks with fully specified instructions in a live Android emulator, at the higher of the two difficulty levels. Success rate in percent; higher is better.

Metric: Success rate (%) on the 24 hard 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: Around February 2027. 11 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1Claude Sonnet 4.670.8#173
2Gemini 3.1 Pro (Preview)66.7#99
3Seed 2.0 Pro62.5#222
4GUI-OWL-1.5-8B33.3
5MAI-UI-8B29.2
6Qwen 3.5 122B A10B25#346
7Qwen 3 VL 32B25#622
8UI-Venus-1.5-8B25
9Qwen 3.5 397B A17B20.8#264
10Qwen 3.5 9B12.5#828
11Qwen 3 VL 8B4.2#917

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