# Distribution Prediction on SMELLNET-MIXTURE (unseen combinations)

Source: [Distribution Prediction on SMELLNET-MIXTURE (unseen combinations)](<https://www.sota2.com/research/sota/distribution-prediction-on-smellnet-mixture-unseen-combinations>)

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

Data updated: 2026-04-15T07:12:09.677Z

Evaluation of model performance on predicting chemical mixture distributions using the unseen combinations split of the SMELLNET-MIXTURE dataset.

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 Prediction |
| Dataset (including any stated split) | SMELLNET-MIXTURE (unseen combinations) |
| Metric | Top-1 Accuracy @ 0.1 |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 4 of 4 |
| 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

- [Top-1 Accuracy @ 0.1](<https://www.sota2.com/research/sota/distribution-prediction-on-smellnet-mixture-unseen-combinations.md?metric=Top-1%20Accuracy%20%40%200.1>): Higher is better; unit: PERCENT.

- [Top-K Accuracy](<https://www.sota2.com/research/sota/distribution-prediction-on-smellnet-mixture-unseen-combinations.md?metric=Top-K%20Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Top-1 Accuracy @ 0.1 | Result date | Report paper |
| --- | --- | --- | --- |
| SCENTFORMER | 16 | Not recorded | 68fa7c0e1e209131cea8c2a2 |
| CNN | 12.4 | Not recorded | 68fa7c0e1e209131cea8c2a2 |
| LSTM | 11.8 | Not recorded | 68fa7c0e1e209131cea8c2a2 |
| MLP | 11.7 | Not recorded | 68fa7c0e1e209131cea8c2a2 |

### SCENTFORMER

Top-1 Accuracy @ 0.1: 16. Result ID: 69df39c547f34ce924c788fa.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c0e1e209131cea8c2a2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c0e1e209131cea8c2a2.md>)

Recorded evaluation configuration: {"Window Size":"50"}. This record does not assert independent reproduction.

### CNN

Top-1 Accuracy @ 0.1: 12.4. Result ID: 69df39c547f34ce924c788f8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c0e1e209131cea8c2a2.md>)

Recorded evaluation configuration: {"Window Size":"50"}. This record does not assert independent reproduction.

### LSTM

Top-1 Accuracy @ 0.1: 11.8. Result ID: 69df39c547f34ce924c788f9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c0e1e209131cea8c2a2.md>)

Recorded evaluation configuration: {"Window Size":"50"}. This record does not assert independent reproduction.

### MLP

Top-1 Accuracy @ 0.1: 11.7. Result ID: 69df39c547f34ce924c788f7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c0e1e209131cea8c2a2.md>)

Recorded evaluation configuration: {"Window Size":"50"}. This record does not assert independent reproduction.

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