KnotBench - Crossing Count: leaderboard
Metric: Accuracy (%) on the 100 C0 items: how many crossings a rendered diagram has; zero-shot with a forced ANSWER line and strict matching, 64K output-token budget, random baseline 0%; higher is better. Source: arxiv.org. Saturation forecast: Around 2029. 4 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 4.7 (Thinking) | 14 |
| 2 | GPT-5 (Thinking) | 11 |
| 3 | Claude Opus 4.7 | 9 |
Interactive version: theaggregate.ai/benchmark?slug=knotbench-crossing-count · How It Works · Data refreshed daily, snapshot 2026-10-07.