SMDD-Bench - Lead Optimization: leaderboard
Metric: Success rate (%) on the 340 SMDD-Bench lead-optimization tasks (improve ADMET objectives while holding constraints and the binding interaction), minimalist ReAct agent harness with RDKit-style tools, 8 Boltz-2 and 15 ADMET-AI oracle calls per task, temperature 1.0, at most 100 turns; success means the submitted molecule passes the task's hidden evaluator; higher is better. Source: arxiv.org. Saturation forecast: Around January 2027. 7 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.4 (Medium) | 57.6 |
| 2 | Gemini 3.1 Pro (Preview) (Medium) | 55.6 |
| 3 | Claude Sonnet 4.6 | 53.5 |
| 4 | Kimi K2.5 (Thinking) | 43.5 |
| 5 | Qwen 3.5 397B A17B | 40 |
| 6 | DeepSeek V3.2 | 34.7 |
| 7 | MiniMax-M2.7 | 27.1 |
Interactive version: theaggregate.ai/benchmark?slug=smdd-bench-lead-optimization · How It Works · Data refreshed daily, snapshot 2026-10-07.