KnotBench: leaderboard
A vision-language model can look at a knot diagram and report what it sees, yet fail to act on that structure. KnotBench pairs an 858,318-image corpus from 1,951 prime-knot prototypes (crossing numbers 3 to 19) with a protocol whose answers are checked against Regina's canonical knot signature. Its 14 tasks span four families, equivalence judgment, move prediction, identification, and cross-modal
Metric: Accuracy (%) (self-reported). Source: benchmarklist.com. Saturation forecast: Around May 2028. 4 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Opus 4.7 (Thinking) | 54.6 | #49 (Claude Opus 4.7) |
| 2 | GPT-5 (Thinking) | 52.25 | #98 (GPT-5) |
| 3 | Claude Opus 4.7 | 51.65 | #49 |
| 4 | GPT-5 | 43 | #98 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=knotbench · How It Works · Data refreshed daily, snapshot 2026-10-20.