# Harmful Compliance Prediction on Locked GLM (test)

Source: [Harmful Compliance Prediction on Locked GLM (test)](<https://www.sota2.com/research/sota/harmful-compliance-prediction-on-locked-glm-test>)

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

Data updated: 2026-05-08T11:01:57.747Z

Evaluation of model performance on predicting harmful compliance using the Locked GLM test set, typically measured using statistical metrics like beta, standard error (SE), z-score, and p-value.

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 | Harmful Compliance Prediction |
| Dataset (including any stated split) | Locked GLM (test) |
| Metric | Beta |
| Unit | SCALAR |
| 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

- [Beta](<https://www.sota2.com/research/sota/harmful-compliance-prediction-on-locked-glm-test.md?metric=Beta>): Higher is better; unit: SCALAR.

- [SE](<https://www.sota2.com/research/sota/harmful-compliance-prediction-on-locked-glm-test.md?metric=SE>): Lower is better; unit: SCALAR.

- [Z-score](<https://www.sota2.com/research/sota/harmful-compliance-prediction-on-locked-glm-test.md?metric=Z-score>): Higher is better; unit: SCALAR.

- [P-value](<https://www.sota2.com/research/sota/harmful-compliance-prediction-on-locked-glm-test.md?metric=P-value>): Lower is better; unit: SCALAR.

## Recorded results

| Method | Beta | Result date | Report paper |
| --- | --- | --- | --- |
| Llama-3.1-8B | 1.489 | Not recorded | 69fd6e555497b3b670c89695 |
| Phi-3.5-mini | 1.25 | Not recorded | 69fd6e555497b3b670c89695 |
| Mistral-Small-3.2 | 1.246 | Not recorded | 69fd6e555497b3b670c89695 |
| Llama-3.1-70B | 0.735 | Not recorded | 69fd6e555497b3b670c89695 |

### Llama-3.1-8B

Beta: 1.489. Result ID: 69fdc29947f34ce924e18abc.

[Reporting paper](<https://www.sota2.com/research/paper/69fd6e555497b3b670c89695.md>)

Recorded evaluation configuration: {"Reference Model":"OLMo-3-Instruct","Frame Reference":"deployment","Interaction term":"model × evaluation"}. This record does not assert independent reproduction.

### Phi-3.5-mini

Beta: 1.25. Result ID: 69fdc29947f34ce924e18abb.

[Reporting paper](<https://www.sota2.com/research/paper/69fd6e555497b3b670c89695.md>)

Recorded evaluation configuration: {"Reference Model":"OLMo-3-Instruct","Frame Reference":"deployment","Interaction term":"model × evaluation"}. This record does not assert independent reproduction.

### Mistral-Small-3.2

Beta: 1.246. Result ID: 69fdc29947f34ce924e18aba.

[Reporting paper](<https://www.sota2.com/research/paper/69fd6e555497b3b670c89695.md>)

Recorded evaluation configuration: {"Reference Model":"OLMo-3-Instruct","Frame Reference":"deployment","Interaction term":"model × evaluation"}. This record does not assert independent reproduction.

### Llama-3.1-70B

Beta: 0.735. Result ID: 69fdc29947f34ce924e18abd.

[Reporting paper](<https://www.sota2.com/research/paper/69fd6e555497b3b670c89695.md>)

Recorded evaluation configuration: {"Reference Model":"OLMo-3-Instruct","Frame Reference":"deployment","Interaction term":"model × evaluation"}. This record does not assert independent reproduction.

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