KnotBench - PD Code Choice: leaderboard
Metric: Accuracy (%) on the 200 D1 items: which of four PD codes describes a rendered diagram; zero-shot with a forced ANSWER line and strict matching, 64K output-token budget, random baseline 25%; higher is better. Source: arxiv.org. Saturation forecast: Around April 2028. 4 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 4.7 (Thinking) | 35.5 |
| 2 | Claude Opus 4.7 | 32.5 |
| 3 | GPT-5 (Thinking) | 30.5 |
Interactive version: theaggregate.ai/benchmark?slug=knotbench-pd-code-choice · How It Works · Data refreshed daily, snapshot 2026-10-07.