OmniGUI - Success Rate: leaderboard

OmniGUI (2026) is a step-level benchmark for smartphone GUI agents in omni-modal environments: at each of 2,579 steps in 709 expert episodes across 29 apps the agent receives a screenshot, synchronous audio and a video clip and predicts the next action, with the true action history given. This board is the percent of episodes in which every step matches the expert action; higher is better.

Metric: Episode success rate (%): share of episodes in which every step is an exact match, over all episodes of OmniGUI (709 expert-demonstrated smartphone episodes, 2,579 action steps in 29 Chinese and English apps; at every step the agent receives the screenshot, a synchronous audio track and a video clip with the ground-truth action history), step-level teacher forcing, temperature 0; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 8 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1Gemini 3 Pro33.4#145
2Gemini 3 Flash30.3#175
3Gemini 2.5 Pro15.5#276
4Gemini 2.5 Flash12.4#463
5Qwen3-Omni5.1#1055
6VITA-1.51.1#3083
7MiniCPM-o-4.50.1#1252
8Baichuan-Omni-1.50#3285

No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=omnigui-success-rate · How It Works · Data refreshed daily, snapshot 2026-11-21.