ADeptS-Bench - Disambiguation (Mobile): leaderboard

Metric: Disambiguation F1 (%; harmonic mean of the precision and recall of the clarification questions against human ground-truth items; 381 mobile tasks; ambiguous GUI decision points reached through a trajectory of screenshots; generated clarification questions matched to ground-truth items by a Gemini 3.1 Pro judge; with severity scoring prompt). Source: arxiv.org. Saturation forecast: Around May 2028. 7 models tracked.

Top models

#ModelScore
1Gemini 3.1 Pro (Preview)58.9
2Claude Opus 4.753.7
3Qwen 3 VL 235B A22B52.8
4GPT-5.445

Interactive version: theaggregate.ai/benchmark?slug=adepts-bench-disambiguation-mobile · How It Works · Data refreshed daily, snapshot 2026-09-29.