DragOn - Slider Manipulation: leaderboard

Metric: Success rate (%) on the slider domain (move an HTML slider to a requested value) 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 December 2026. 8 models tracked.

Top models

#ModelScore
1Claude Opus 4.757.2
2GPT-5.445.6
3Qwen 3.5 397B A17B39.6
4Claude Sonnet 4.526
5Kimi K2.5 (Non-reasoning)16
6Qwen 3.5 35B A3B4.8

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