MobiFlow: leaderboard
Metric: Success rate (%) in the base scenario, the share of tasks whose goal state is reached on MobiFlow's 240 real-world tasks in 20 third-party Android apps, scored on task-completion state graphs fused from real trajectories, at most 50 steps; general models in the paper's shared execution framework (OmniParser marks actionable elements; OpenRouter, temperature 0); higher is better. Source: arxiv.org. Saturation forecast: Around January 2027. 6 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5 | 49.7 |
| 2 | Claude Opus 4.1 | 43.6 |
| 3 | Gemini 3 Flash | 40.2 |
| 4 | Gemini 2.5 Pro | 38.7 |
| 5 | Gemini 2.5 Flash | 30.7 |
| 6 | Grok 4 | 8.3 |
Interactive version: theaggregate.ai/benchmark?slug=mobiflow · How It Works · Data refreshed daily, snapshot 2026-10-07.