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
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 4.7 | 57.2 |
| 2 | GPT-5.4 | 45.6 |
| 3 | Qwen 3.5 397B A17B | 39.6 |
| 4 | Claude Sonnet 4.5 | 26 |
| 5 | Kimi K2.5 (Non-reasoning) | 16 |
| 6 | Qwen 3.5 35B A3B | 4.8 |
Interactive version: theaggregate.ai/benchmark?slug=dragon-slider-manipulation · How It Works · Data refreshed daily, snapshot 2026-09-29.