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
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Sonnet 4.6 | 70.8 | #173 |
| 2 | Gemini 3.1 Pro (Preview) | 66.7 | #99 |
| 3 | Seed 2.0 Pro | 62.5 | #222 |
| 4 | GUI-OWL-1.5-8B | 33.3 | |
| 5 | MAI-UI-8B | 29.2 | |
| 6 | Qwen 3.5 122B A10B | 25 | #346 |
| 7 | Qwen 3 VL 32B | 25 | #622 |
| 8 | UI-Venus-1.5-8B | 25 | |
| 9 | Qwen 3.5 397B A17B | 20.8 | #264 |
| 10 | Qwen 3.5 9B | 12.5 | #828 |
| 11 | Qwen 3 VL 8B | 4.2 | #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.