# Safety Classification on Bloom safety filter benchmark 100 examples (corrected) (test)

Source: [Safety Classification on Bloom safety filter benchmark 100 examples (corrected) (test)](<https://www.sota2.com/research/sota/safety-classification-on-bloom-safety-filter-benchmark-100-examples-corrected-test>)

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

Data updated: 2026-03-05T06:57:18.912Z

Evaluation of model performance on the 100-example test split of the corrected Bloom safety filter benchmark using standard classification metrics (Accuracy, Precision, Recall, F1).

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 | Safety Classification |
| Dataset (including any stated split) | Bloom safety filter benchmark 100 examples (corrected) (test) |
| Metric | Accuracy |
| 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

- [Accuracy](<https://www.sota2.com/research/sota/safety-classification-on-bloom-safety-filter-benchmark-100-examples-corrected-test.md?metric=Accuracy>): Higher is better; unit: PERCENT.

- [Precision](<https://www.sota2.com/research/sota/safety-classification-on-bloom-safety-filter-benchmark-100-examples-corrected-test.md?metric=Precision>): Higher is better; unit: PERCENT.

- [Recall](<https://www.sota2.com/research/sota/safety-classification-on-bloom-safety-filter-benchmark-100-examples-corrected-test.md?metric=Recall>): Higher is better; unit: PERCENT.

- [F1 Score](<https://www.sota2.com/research/sota/safety-classification-on-bloom-safety-filter-benchmark-100-examples-corrected-test.md?metric=F1%20Score>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| Bloom Safety Filter | 100 | Not recorded | 68fa7bef1e209131cea8b6ba |
| Bloom Safety Filter | 100 | Not recorded | 68fa7bef1e209131cea8b6ba |
| Bloom Safety Filter | 100 | Not recorded | 68fa7bef1e209131cea8b6ba |
| Bloom Safety Filter | 93 | Not recorded | 68fa7bef1e209131cea8b6ba |
| Bloom Safety Filter | 92 | Not recorded | 68fa7bef1e209131cea8b6ba |
| Bloom Safety Filter | 91 | Not recorded | 68fa7bef1e209131cea8b6ba |
| Bloom Safety Filter | 90 | Not recorded | 68fa7bef1e209131cea8b6ba |

### Bloom Safety Filter

Accuracy: 100. Result ID: 69a928776dbb7075b951f7ea.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bef1e209131cea8b6ba.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7bef1e209131cea8b6ba.md>)

Recorded evaluation configuration: {"Category":"2: Body Image","Evaluation protocol":"Strict","Temperature":"0"}. This record does not assert independent reproduction.

### Bloom Safety Filter

Accuracy: 100. Result ID: 69a928776dbb7075b951f7ec.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bef1e209131cea8b6ba.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7bef1e209131cea8b6ba.md>)

Recorded evaluation configuration: {"Category":"4: Neg. Mindsets","Evaluation protocol":"Strict","Temperature":"0"}. This record does not assert independent reproduction.

### Bloom Safety Filter

Accuracy: 100. Result ID: 69a928776dbb7075b951f7ed.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bef1e209131cea8b6ba.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7bef1e209131cea8b6ba.md>)

Recorded evaluation configuration: {"Category":"5: Inacc. Advice","Evaluation protocol":"Strict","Temperature":"0"}. This record does not assert independent reproduction.

### Bloom Safety Filter

Accuracy: 93. Result ID: 69a928776dbb7075b951f7e9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bef1e209131cea8b6ba.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7bef1e209131cea8b6ba.md>)

Recorded evaluation configuration: {"Category":"1: Bodily Harm","Evaluation protocol":"Strict","Temperature":"0"}. This record does not assert independent reproduction.

### Bloom Safety Filter

Accuracy: 92. Result ID: 69a928776dbb7075b951f7ef.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bef1e209131cea8b6ba.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7bef1e209131cea8b6ba.md>)

Recorded evaluation configuration: {"Category":"Overall","Evaluation protocol":"Relaxed","Temperature":"0"}. This record does not assert independent reproduction.

### Bloom Safety Filter

Accuracy: 91. Result ID: 69a928776dbb7075b951f7ee.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bef1e209131cea8b6ba.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7bef1e209131cea8b6ba.md>)

Recorded evaluation configuration: {"Category":"Overall","Evaluation protocol":"Strict","Temperature":"0"}. This record does not assert independent reproduction.

### Bloom Safety Filter

Accuracy: 90. Result ID: 69a928776dbb7075b951f7eb.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bef1e209131cea8b6ba.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7bef1e209131cea8b6ba.md>)

Recorded evaluation configuration: {"Category":"3: Mental Health","Evaluation protocol":"Strict","Temperature":"0"}. This record does not assert independent reproduction.

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