# Out-of-Distribution Detection on CLINC SMALL (test)

Source: [Out-of-Distribution Detection on CLINC SMALL (test)](<https://www.sota2.com/research/sota/out-of-distribution-detection-on-clinc-small-test>)

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

Data updated: 2026-02-26T05:25:53.546Z

Evaluation of Out-of-Distribution Detection performance using the test split of the CLINC SMALL dataset, measured using metrics like AUROC.

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 | Out-of-Distribution Detection |
| Dataset (including any stated split) | CLINC SMALL (test) |
| Metric | AUROC |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 17 of 17 |
| 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

- [AUROC](<https://www.sota2.com/research/sota/out-of-distribution-detection-on-clinc-small-test.md?metric=AUROC>): Higher is better; unit: PERCENT.

## Recorded results

| Method | AUROC | Result date | Report paper |
| --- | --- | --- | --- |
| POE+Energy | 96.85 | Not recorded | 68fa701f1e209131cea49301 |
| MCL+Energy | 96.82 | Not recorded | 68fa701f1e209131cea49301 |
| Maha | 96.81 | Not recorded | 68fa701f1e209131cea49301 |
| MCL+Maha | 96.81 | Not recorded | 68fa701f1e209131cea49301 |
| SCL+Maha | 96.8 | Not recorded | 68fa701f1e209131cea49301 |
| SCL+Energy | 96.71 | Not recorded | 68fa701f1e209131cea49301 |
| Energy | 96.35 | Not recorded | 68fa701f1e209131cea49301 |
| POE+Maha | 96.19 | Not recorded | 68fa701f1e209131cea49301 |
| KNN-cosine | 96.03 | Not recorded | 68fa701f1e209131cea49301 |
| KNN-euclidean | 96.02 | Not recorded | 68fa701f1e209131cea49301 |
| ODIN | 96.01 | Not recorded | 68fa701f1e209131cea49301 |
| ReAct | 96.01 | Not recorded | 68fa701f1e209131cea49301 |
| POE+MSP | 95.92 | Not recorded | 68fa701f1e209131cea49301 |
| SCL+MSP | 95.42 | Not recorded | 68fa701f1e209131cea49301 |
| MCL+MSP | 95.22 | Not recorded | 68fa701f1e209131cea49301 |
| MSP | 95.14 | Not recorded | 68fa701f1e209131cea49301 |
| DICE | 95.02 | Not recorded | 68fa701f1e209131cea49301 |

### POE+Energy

AUROC: 96.85. Result ID: 69911fbc3a6c31484905de49.

[Reporting paper](<https://www.sota2.com/research/paper/68fa701f1e209131cea49301.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa701f1e209131cea49301.md>)

[Implementation](<https://github.com/kimjeyoung/Pseudo_OutlierExposure>)

Recorded evaluation configuration: {"Backbone":"BERT"}. This record does not assert independent reproduction.

### MCL+Energy

AUROC: 96.82. Result ID: 69911fbc3a6c31484905de48.

[Reporting paper](<https://www.sota2.com/research/paper/68fa701f1e209131cea49301.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ba51e209131cea2f89c.md>)

Recorded evaluation configuration: {"Backbone":"BERT"}. This record does not assert independent reproduction.

### Maha

AUROC: 96.81. Result ID: 69911fbc3a6c31484905de3f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa701f1e209131cea49301.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa64f91e209131cea077ac.md>)

[Implementation](<https://github.com/pokaxpoka/deep_Mahalanobis_detector>)

Recorded evaluation configuration: {"Backbone":"BERT"}. This record does not assert independent reproduction.

### MCL+Maha

AUROC: 96.81. Result ID: 69911fbc3a6c31484905de4b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa701f1e209131cea49301.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ba51e209131cea2f89c.md>)

Recorded evaluation configuration: {"Backbone":"BERT"}. This record does not assert independent reproduction.

### SCL+Maha

AUROC: 96.8. Result ID: 69911fbc3a6c31484905de4a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa701f1e209131cea49301.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa697f1e209131cea22756.md>)

Recorded evaluation configuration: {"Backbone":"BERT"}. This record does not assert independent reproduction.

### SCL+Energy

AUROC: 96.71. Result ID: 69911fbc3a6c31484905de47.

[Reporting paper](<https://www.sota2.com/research/paper/68fa701f1e209131cea49301.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa697f1e209131cea22756.md>)

Recorded evaluation configuration: {"Backbone":"BERT"}. This record does not assert independent reproduction.

### Energy

AUROC: 96.35. Result ID: 69911fbc3a6c31484905de3d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa701f1e209131cea49301.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69cc1e209131cea24242.md>)

Recorded evaluation configuration: {"Backbone":"BERT"}. This record does not assert independent reproduction.

### POE+Maha

AUROC: 96.19. Result ID: 69911fbc3a6c31484905de4c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa701f1e209131cea49301.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa701f1e209131cea49301.md>)

[Implementation](<https://github.com/kimjeyoung/Pseudo_OutlierExposure>)

Recorded evaluation configuration: {"Backbone":"BERT"}. This record does not assert independent reproduction.

### KNN-cosine

AUROC: 96.03. Result ID: 69911fbc3a6c31484905de42.

[Reporting paper](<https://www.sota2.com/research/paper/68fa701f1e209131cea49301.md>)

Recorded evaluation configuration: {"Backbone":"BERT"}. This record does not assert independent reproduction.

### KNN-euclidean

AUROC: 96.02. Result ID: 69911fbc3a6c31484905de43.

[Reporting paper](<https://www.sota2.com/research/paper/68fa701f1e209131cea49301.md>)

Recorded evaluation configuration: {"Backbone":"BERT"}. This record does not assert independent reproduction.

### ODIN

AUROC: 96.01. Result ID: 69911fbc3a6c31484905de3e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa701f1e209131cea49301.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa684a1e209131cea1b26f.md>)

[Implementation](<https://github.com/facebookresearch/odin>)

Recorded evaluation configuration: {"Backbone":"BERT"}. This record does not assert independent reproduction.

### ReAct

AUROC: 96.01. Result ID: 69911fbc3a6c31484905de40.

[Reporting paper](<https://www.sota2.com/research/paper/68fa701f1e209131cea49301.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b4f1e209131cea2d8b5.md>)

[Implementation](<https://github.com/deeplearning-wisc/react.git>)

Recorded evaluation configuration: {"Backbone":"BERT"}. This record does not assert independent reproduction.

### POE+MSP

AUROC: 95.92. Result ID: 69911fbc3a6c31484905de46.

[Reporting paper](<https://www.sota2.com/research/paper/68fa701f1e209131cea49301.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa701f1e209131cea49301.md>)

[Implementation](<https://github.com/kimjeyoung/Pseudo_OutlierExposure>)

Recorded evaluation configuration: {"Backbone":"BERT"}. This record does not assert independent reproduction.

### SCL+MSP

AUROC: 95.42. Result ID: 69911fbc3a6c31484905de44.

[Reporting paper](<https://www.sota2.com/research/paper/68fa701f1e209131cea49301.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa697f1e209131cea22756.md>)

Recorded evaluation configuration: {"Backbone":"BERT"}. This record does not assert independent reproduction.

### MCL+MSP

AUROC: 95.22. Result ID: 69911fbc3a6c31484905de45.

[Reporting paper](<https://www.sota2.com/research/paper/68fa701f1e209131cea49301.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ba51e209131cea2f89c.md>)

Recorded evaluation configuration: {"Backbone":"BERT"}. This record does not assert independent reproduction.

### MSP

AUROC: 95.14. Result ID: 69911fbc3a6c31484905de3c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa701f1e209131cea49301.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa64e41e209131cea0731a.md>)

[Implementation](<https://www.sota2.com/github.com/hendrycks/error-detection>)

Recorded evaluation configuration: {"Backbone":"BERT"}. This record does not assert independent reproduction.

### DICE

AUROC: 95.02. Result ID: 69911fbc3a6c31484905de41.

[Reporting paper](<https://www.sota2.com/research/paper/68fa701f1e209131cea49301.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6cfc1e209131cea371c4.md>)

[Implementation](<https://github.com/deeplearning-wisc/dice.git>)

Recorded evaluation configuration: {"Backbone":"BERT"}. This record does not assert independent reproduction.

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