Knossos (Edge F1): leaderboard
Metric: Edge F1 (%), macro-averaged over six diagram domains (1,200 test diagrams), direct full-graph generation. Source: arxiv.org. Saturation forecast: Around January 2027. 10 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.6 Sol | 81.1 |
| 2 | Claude Opus 5 | 70.4 |
| 3 | GPT-4o | 41.2 |
Interactive version: theaggregate.ai/benchmark?slug=knossos-edge-f1 · How It Works · Data refreshed daily, snapshot 2026-10-07.