Rule2DRC: leaderboard

Metric: Success rate (%; one sampled DRC script per rule with the 60K-token KLayout DRC API documentation in the prompt, correct when its violation output matches the ground-truth script on every evaluation layout; 1,000 rules, mean of 30 runs). Source: arxiv.org. Saturation forecast: Around January 2027. 3 models tracked.

Top models

#ModelScore
1GPT-OSS-120B (Medium)32.5
2GPT-OSS-20B (Medium)16.9
3Qwen 3 30B A3B 2507 Instruct14.1

Interactive version: theaggregate.ai/benchmark?slug=rule2drc · How It Works · Data refreshed daily, snapshot 2026-09-26.