# Uncertainty Quantification on SVHN

Source: [Uncertainty Quantification on SVHN](<https://www.sota2.com/research/sota/uncertainty-quantification-on-svhn>)

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

Data updated: 2026-06-01T08:06:05.470Z

Evaluation of model performance on Uncertainty Quantification using the SVHN 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 | Uncertainty Quantification |
| Dataset (including any stated split) | SVHN |
| Metric | V-ID Score |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 7 of 7 |
| 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

- [V-ID Score](<https://www.sota2.com/research/sota/uncertainty-quantification-on-svhn.md?metric=V-ID%20Score>): Higher is better; unit: PERCENT.

- [V-OOD Score](<https://www.sota2.com/research/sota/uncertainty-quantification-on-svhn.md?metric=V-OOD%20Score>): Higher is better; unit: PERCENT.

- [MI Score (ID)](<https://www.sota2.com/research/sota/uncertainty-quantification-on-svhn.md?metric=MI%20Score%20(ID)>): Higher is better; unit: PERCENT.

- [MI Score (OOD)](<https://www.sota2.com/research/sota/uncertainty-quantification-on-svhn.md?metric=MI%20Score%20(OOD)>): Higher is better; unit: PERCENT.

- [LPPD](<https://www.sota2.com/research/sota/uncertainty-quantification-on-svhn.md?metric=LPPD>): Higher is better; unit: SCALAR.

- [Total Time (s)](<https://www.sota2.com/research/sota/uncertainty-quantification-on-svhn.md?metric=Total%20Time%20(s)>): Lower is better; unit: TIME.

- [Memory Usage (MB)](<https://www.sota2.com/research/sota/uncertainty-quantification-on-svhn.md?metric=Memory%20Usage%20(MB)>): Lower is better; unit: SIZE.

## Recorded results

| Method | V-ID Score | Result date | Report paper |
| --- | --- | --- | --- |
| LL-GLM | 91.54 | Not recorded | 6a1d1214dbd7150506f84007 |
| LLA | 91.51 | Not recorded | 6a1d1214dbd7150506f84007 |
| DNN-GLM | 90.97 | Not recorded | 6a1d1214dbd7150506f84007 |
| MC | 90.81 | Not recorded | 6a1d1214dbd7150506f84007 |
| SWAG | 88.66 | Not recorded | 6a1d1214dbd7150506f84007 |
| DE | 84.69 | Not recorded | 6a1d1214dbd7150506f84007 |
| SMS-UBU | 51.36 | Not recorded | 6a1d1214dbd7150506f84007 |

### LL-GLM

V-ID Score: 91.54. Result ID: 6a1d3d5cfbc373592c1642c4.

[Reporting paper](<https://www.sota2.com/research/paper/6a1d1214dbd7150506f84007.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a1d1214dbd7150506f84007.md>)

Recorded evaluation configuration: {"Backbone":"ResNet50"}. This record does not assert independent reproduction.

### LLA

V-ID Score: 91.51. Result ID: 6a1d3d5cfbc373592c1642c6.

[Reporting paper](<https://www.sota2.com/research/paper/6a1d1214dbd7150506f84007.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6bfe1e209131cea31830.md>)

Recorded evaluation configuration: {"Backbone":"ResNet50"}. This record does not assert independent reproduction.

### DNN-GLM

V-ID Score: 90.97. Result ID: 6a1d3d5cfbc373592c1642c3.

[Reporting paper](<https://www.sota2.com/research/paper/6a1d1214dbd7150506f84007.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c2f1e209131cea8ce7f.md>)

Recorded evaluation configuration: {"Backbone":"ResNet50"}. This record does not assert independent reproduction.

### MC

V-ID Score: 90.81. Result ID: 6a1d3d5cfbc373592c1642c8.

[Reporting paper](<https://www.sota2.com/research/paper/6a1d1214dbd7150506f84007.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa62d31e209131ce9fb5ff.md>)

Recorded evaluation configuration: {"Backbone":"ResNet50"}. This record does not assert independent reproduction.

### SWAG

V-ID Score: 88.66. Result ID: 6a1d3d5cfbc373592c1642c7.

[Reporting paper](<https://www.sota2.com/research/paper/6a1d1214dbd7150506f84007.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66e71e209131cea130c6.md>)

Recorded evaluation configuration: {"Backbone":"ResNet50"}. This record does not assert independent reproduction.

### DE

V-ID Score: 84.69. Result ID: 6a1d3d5cfbc373592c1642c5.

[Reporting paper](<https://www.sota2.com/research/paper/6a1d1214dbd7150506f84007.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa63bc1e209131cea0084f.md>)

Recorded evaluation configuration: {"Backbone":"ResNet50"}. This record does not assert independent reproduction.

### SMS-UBU

V-ID Score: 51.36. Result ID: 6a1d3d5cfbc373592c1642c9.

[Reporting paper](<https://www.sota2.com/research/paper/6a1d1214dbd7150506f84007.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa5d1a1e209131ce9d7298.md>)

Recorded evaluation configuration: {"Backbone":"ResNet50"}. This record does not assert independent reproduction.

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