URSA - Drugs and Clinicals ChemCensor: leaderboard
Metric: Average ChemCensor plausibility score (out of 5) per reaction step along the best route per target, averaged over the 100 URSA-drugs&clinicals-2026 approved drugs and clinical candidates; URSA-minor-1.1.0-U2 configuration with ChemCensor v1.2.0 and the U2 USPTO precedent database; default reasoning effort; higher is better. Source: arxiv.org. Saturation forecast: Around August 2027. 17 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.5 | 2.43 |
| 2 | Gemini 3.1 Pro (Preview) | 2.42 |
| 3 | Grok 4.1 | 2.01 |
| 4 | Claude Opus 4.8 | 1.99 |
| 5 | Claude Opus 4.7 | 1.97 |
| 6 | Kimi K2.5 | 1.78 |
| 7 | Claude Opus 4.5 | 1.71 |
| 8 | Qwen 3.5 397B A17B | 1.7 |
| 9 | Claude Opus 4.6 | 1.67 |
| 10 | Claude Sonnet 4.5 | 1.53 |
| 11 | GLM-5 | 1.48 |
| 12 | Claude Sonnet 4.6 | 1.44 |
| 13 | GPT-5.4 | 1.43 |
| 14 | GPT-5.2 | 1.33 |
| 15 | DeepSeek V3.2 | 1.06 |
Interactive version: theaggregate.ai/benchmark?slug=ursa-drugs-and-clinicals-chemcensor · How It Works · Data refreshed daily, snapshot 2026-09-29.