ADeptS-Bench - Disambiguation (Desktop): leaderboard

Metric: Disambiguation F1 (%; harmonic mean of the precision and recall of the clarification questions against human ground-truth items; 363 desktop 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 2030. 7 models tracked.

Top models

#ModelScore
1Claude Opus 4.747.6
2Qwen 3 VL 235B A22B46.3
3Gemini 3.1 Pro (Preview)39.8
4GPT-5.430.3

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