KnotBench - Crossing Count: leaderboard

The C0 task of KnotBench (2026, The Gordian Knot for VLMs): judge how many crossings a rendered diagram has, with answers checked against Regina canonical knot signatures. The score is accuracy in percent under strict answer matching, with a random baseline of 0 percent; higher is better.

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. 2 models tracked. Updated 7 Oct 2026.

Top models

#ModelSettingScoreOverall rank
1Claude Opus 4.7Thinking14#86
2GPT-5Thinking11#185

No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=knotbench-crossing-count · How It Works · Data refreshed daily, snapshot 2026-11-22.