SciDiagramEdit - Semantic Faithfulness: leaderboard
Metric: No-skill pairwise win rate (%). Source: arxiv.org. 4 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.5 | 74.5 |
| 2 | GPT-5.4 | 70 |
| 3 | GPT-5.3 | 65.9 |
| 4 | GPT-5.1 | 22.4 |
Interactive version: theaggregate.ai/benchmark?slug=scidiagramedit-semantic-faithfulness · How It Works · Data refreshed daily, snapshot 2026-09-05.