Description-guided molecule generation
The significance of description-based molecule generation lies in its potential to streamline the process of molecular design by enabling the production of molecules that directly meet the criteria outlined in a given description. This facilitates a more targeted approach in the creation and optimization of novel molecules, with applications in diverse fields such as drug discovery and materials science.
Papers
Showing 1–2 of 2 papers
Benchmark Results
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | Claude-3.5 | wAcc | 35.92 | — | Unverified |
| 2 | Gemini-1.5-pro | wAcc | 34.8 | — | Unverified |
| 3 | GPT-4-turbo | wAcc | 34.23 | — | Unverified |
| 4 | GPT-4o | wAcc | 32.29 | — | Unverified |
| 5 | Claude-3 | wAcc | 30.47 | — | Unverified |
| 6 | Llama-3.1-8B (OpenMolIns-large) | wAcc | 27.22 | — | Unverified |
| 7 | Galactica-125M (OpenMolIns-xlarge) | wAcc | 25.73 | — | Unverified |
| 8 | Llama3-70B-Instruct (INT4) | wAcc | 23.93 | — | Unverified |
| 9 | Galactica-125M (OpenMolIns-large) | wAcc | 23.42 | — | Unverified |
| 10 | Galactica-125M (OpenMolIns-medium) | wAcc | 19.89 | — | Unverified |