KnotBench - Same Canonical PD (Images): leaderboard
Metric: Accuracy (%) on the 200 A3-I items: whether two diagrams have the same canonical PD code; zero-shot with a forced ANSWER line and strict matching, 64K output-token budget, random baseline 50%; higher is better. Source: arxiv.org. Saturation forecast: Around January 2027. 4 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 4.7 | 90.5 |
| 2 | Claude Opus 4.7 (Thinking) | 90.5 |
| 3 | GPT-5 (Thinking) | 74.5 |
Interactive version: theaggregate.ai/benchmark?slug=knotbench-same-canonical-pd-images · How It Works · Data refreshed daily, snapshot 2026-10-07.