KnotBench - PD Code Match: leaderboard
Metric: Accuracy (%) on the 200 D0 items: whether a PD code describes a rendered diagram; 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 June 2027. 4 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5 (Thinking) | 58 |
| 2 | Claude Opus 4.7 | 50.5 |
| 3 | Claude Opus 4.7 (Thinking) | 47 |
Interactive version: theaggregate.ai/benchmark?slug=knotbench-pd-code-match · How It Works · Data refreshed daily, snapshot 2026-10-07.