SciDiagramEdit - Aesthetic Preference — leaderboard
Metric: No-skill pairwise win rate (%). Source: arxiv.org. 3 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.5 | 46.6 |
| 2 | GPT-5.4 | 36 |
| 3 | GPT-5.1 | 16.8 |
Interactive version: aibenchmarks.dev/benchmark?slug=scidiagramedit-aesthetic-preference · How the rankings work · Data refreshed daily, snapshot 2026-07-18.