URSA - Expert-2026 ChemCensor: leaderboard
Route plausibility on the 100 novel drug-like URSA-expert-2026 targets (Insilico Medicine, 2026): the mean ChemCensor score, from 0 to 5, per reaction step along the best proposed route of each target, averaged over targets. Higher is better.
Metric: Average ChemCensor plausibility score (out of 5) per reaction step along the best route per target, averaged over the 100 URSA-expert-2026 novel targets; 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 July 2028. 17 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.5 | 1.62 | #49 |
| 2 | Gemini 3.1 Pro (Preview) | 1.46 | #94 |
| 3 | Kimi K2.5 | 1.44 | #256 |
| 4 | Claude Opus 4.8 | 1.3 | #56 |
| 5 | Claude Opus 4.7 | 1.24 | #79 |
| 6 | Grok 4.1 | 1.22 | #476 |
| 7 | Claude Opus 4.5 | 1.03 | #156 |
| 8 | Claude Opus 4.6 | 1.02 | #102 |
| 9 | Qwen 3.5 397B A17B | 1 | #246 |
| 10 | GLM-5 | 1 | #260 |
| 11 | Claude Sonnet 4.6 | 0.99 | #161 |
| 12 | Claude Sonnet 4.5 | 0.98 | #250 |
| 13 | Grok 4.3 | 0.94 | #333 |
| 14 | DeepSeek V3.2 | 0.85 | #406 |
| 15 | GPT-5.4 | 0.71 | #123 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=ursa-expert-2026-chemcensor · How It Works · Data refreshed daily, snapshot 2026-11-13.