KnotBench — leaderboard
Metric: Accuracy (%) (self-reported). Source: benchmarklist.com. 2 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 4.7 | 54.6 |
| 2 | GPT-5 | 52.25 |
Interactive version: theaggregate.ai/benchmark?slug=knotbench · How the rankings work · Data refreshed daily, snapshot 2026-07-22.