DragOn: leaderboard

Metric: Success rate (%) on the four drag domains (text highlighting, spreadsheet cell selection, slider manipulation and slide element resizing) of the private 1,000-example DragOn test split (250 per domain): from one screenshot and instruction the model outputs the drag's start and end points as JSON, and both must fall inside the pixel-aligned source and target boxes; each model at its documented settings (Claude extended thinking off, Kimi-K2.5 reasoning off, local Qwen and Holo models with chain-of-thought on); higher is better. Source: arxiv.org. Saturation forecast: Around July 2027. 8 models tracked.

Top models

#ModelScore
1Claude Opus 4.727.7
2GPT-5.425.7
3Qwen 3.5 397B A17B21.5
4Kimi K2.5 (Non-reasoning)11.6
5Claude Sonnet 4.510.7
6Qwen 3.5 35B A3B2.3

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