# Distribution-learning on GuacaMol (test)

Source: [Distribution-learning on GuacaMol (test)](<https://www.sota2.com/research/sota/distribution-learning-on-guacamol-test>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-02-26T06:08:07.434Z

Evaluation of generative model performance on the GuacaMol dataset (test split), focusing on molecular distribution learning capabilities, measured by metrics like Validity, Uniqueness, Novelty, KL Divergence, and FCD.

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | Distribution-learning |
| Dataset (including any stated split) | GuacaMol (test) |
| Metric | Validity |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 8 of 8 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [Validity](<https://www.sota2.com/research/sota/distribution-learning-on-guacamol-test.md?metric=Validity>): Higher is better; unit: PERCENT.

- [Uniqueness](<https://www.sota2.com/research/sota/distribution-learning-on-guacamol-test.md?metric=Uniqueness>): Higher is better; unit: PERCENT.

- [Novelty](<https://www.sota2.com/research/sota/distribution-learning-on-guacamol-test.md?metric=Novelty>): Higher is better; unit: PERCENT.

- [KL Divergence](<https://www.sota2.com/research/sota/distribution-learning-on-guacamol-test.md?metric=KL%20Divergence>): Lower is better; unit: SCALAR.

- [FCD](<https://www.sota2.com/research/sota/distribution-learning-on-guacamol-test.md?metric=FCD>): Lower is better; unit: SCALAR.

## Recorded results

| Method | Validity | Result date | Report paper |
| --- | --- | --- | --- |
| VGAE-MCTS | 100 | Not recorded | 68fa492f1e209131ce9354fd |
| ChemBFN\* | 100 | Not recorded | 68fa492f1e209131ce9354fd |
| ChemBFN\* | 100 | Not recorded | 68fa492f1e209131ce9354fd |
| ChemBFN\* | 100 | Not recorded | 68fa492f1e209131ce9354fd |
| MolGPT | 98.1 | Not recorded | 68fa492f1e209131ce9354fd |
| SMILES LSTM | 95.9 | Not recorded | 68fa492f1e209131ce9354fd |
| DiGress | 85.2 | Not recorded | 68fa492f1e209131ce9354fd |
| ChemBFN | 80.7 | Not recorded | 68fa492f1e209131ce9354fd |

### VGAE-MCTS

Validity: 100. Result ID: 698b9f147a967eddb7701811.

[Reporting paper](<https://www.sota2.com/research/paper/68fa492f1e209131ce9354fd.md>)

Recorded evaluation configuration: {"Model Category":"ARs"}. This record does not assert independent reproduction.

### ChemBFN\*

Validity: 100. Result ID: 698b9f147a967eddb7701814.

[Reporting paper](<https://www.sota2.com/research/paper/68fa492f1e209131ce9354fd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa492f1e209131ce9354fd.md>)

[Implementation](<https://github.com/Augus1999/bayesian-flow-network-for-chemistry>)

Recorded evaluation configuration: {"Model Category":"BFNs","Discretization steps":"10"}. This record does not assert independent reproduction.

### ChemBFN\*

Validity: 100. Result ID: 698b9f147a967eddb7701815.

[Reporting paper](<https://www.sota2.com/research/paper/68fa492f1e209131ce9354fd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa492f1e209131ce9354fd.md>)

[Implementation](<https://github.com/Augus1999/bayesian-flow-network-for-chemistry>)

Recorded evaluation configuration: {"Model Category":"BFNs","Discretization steps":"100"}. This record does not assert independent reproduction.

### ChemBFN\*

Validity: 100. Result ID: 698b9f147a967eddb7701816.

[Reporting paper](<https://www.sota2.com/research/paper/68fa492f1e209131ce9354fd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa492f1e209131ce9354fd.md>)

[Implementation](<https://github.com/Augus1999/bayesian-flow-network-for-chemistry>)

Recorded evaluation configuration: {"Model Category":"BFNs","Discretization steps":"1k"}. This record does not assert independent reproduction.

### MolGPT

Validity: 98.1. Result ID: 698b9f147a967eddb770180f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa492f1e209131ce9354fd.md>)

Recorded evaluation configuration: {"Model Category":"ARs"}. This record does not assert independent reproduction.

### SMILES LSTM

Validity: 95.9. Result ID: 698b9f147a967eddb7701810.

[Reporting paper](<https://www.sota2.com/research/paper/68fa492f1e209131ce9354fd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa3ddd1e209131ce8e3ab1.md>)

Recorded evaluation configuration: {"Model Category":"ARs"}. This record does not assert independent reproduction.

### DiGress

Validity: 85.2. Result ID: 698b9f147a967eddb7701812.

[Reporting paper](<https://www.sota2.com/research/paper/68fa492f1e209131ce9354fd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f661e209131cea45555.md>)

Recorded evaluation configuration: {"Model Category":"DMs"}. This record does not assert independent reproduction.

### ChemBFN

Validity: 80.7. Result ID: 698b9f147a967eddb7701813.

[Reporting paper](<https://www.sota2.com/research/paper/68fa492f1e209131ce9354fd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa492f1e209131ce9354fd.md>)

[Implementation](<https://github.com/Augus1999/bayesian-flow-network-for-chemistry>)

Recorded evaluation configuration: {"Model Category":"BFNs","Discretization steps":"1k"}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.