# Safety and Helpfulness Evaluation on Phone-Harm Harm-150

Source: [Safety and Helpfulness Evaluation on Phone-Harm Harm-150](<https://www.sota2.com/research/sota/safety-and-helpfulness-evaluation-on-phone-harm-harm-150>)

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

Data updated: 2026-04-13T09:10:06.012Z

Evaluation of model safety and helpfulness performance using the Phone-Harm Harm-150 dataset, measured by HR, GAR, IF1, mHR, and OIR.

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 and Helpfulness Evaluation |
| Dataset (including any stated split) | Phone-Harm Harm-150 |
| Metric | HR |
| Unit | SCALAR |
| Direction | Lower is better |
| Results loaded | 8 of 8 |
| 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

- [HR](<https://www.sota2.com/research/sota/safety-and-helpfulness-evaluation-on-phone-harm-harm-150.md?metric=HR>): Lower is better; unit: SCALAR.

- [GAR](<https://www.sota2.com/research/sota/safety-and-helpfulness-evaluation-on-phone-harm-harm-150.md?metric=GAR>): Higher is better; unit: PERCENT.

- [IF1 Score](<https://www.sota2.com/research/sota/safety-and-helpfulness-evaluation-on-phone-harm-harm-150.md?metric=IF1%20Score>): Higher is better; unit: SCALAR.

- [mHR](<https://www.sota2.com/research/sota/safety-and-helpfulness-evaluation-on-phone-harm-harm-150.md?metric=mHR>): Lower is better; unit: SCALAR.

- [OIR](<https://www.sota2.com/research/sota/safety-and-helpfulness-evaluation-on-phone-harm-harm-150.md?metric=OIR>): Lower is better; unit: SCALAR.

## Recorded results

| Method | HR | Result date | Report paper |
| --- | --- | --- | --- |
| GPT-5 | 0.4 | Not recorded | 69dc786b7d0172140ec789a2 |
| Gemini-3 | 0.84 | Not recorded | 69dc786b7d0172140ec789a2 |
| AutoGLM-VLM | 3.58 | Not recorded | 69dc786b7d0172140ec789a2 |
| AutoGLM | 4.3 | Not recorded | 69dc786b7d0172140ec789a2 |
| AutoGLM | 4.3 | Not recorded | 69dc786b7d0172140ec789a2 |
| CORA | 4.37 | Not recorded | 69dc786b7d0172140ec789a2 |
| UI-TARS-1.5 | 5.73 | Not recorded | 69dc786b7d0172140ec789a2 |
| AutoGLM | 24.37 | Not recorded | 69dc786b7d0172140ec789a2 |

### GPT-5

HR: 0.4. Result ID: 69dcb29e47f34ce924c3db09.

[Reporting paper](<https://www.sota2.com/research/paper/69dc786b7d0172140ec789a2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/695f39f053fdd5c361743ecb.md>)

Recorded evaluation configuration: {"Type":"Base"}. This record does not assert independent reproduction.

### Gemini-3

HR: 0.84. Result ID: 69dcb29e47f34ce924c3db0a.

[Reporting paper](<https://www.sota2.com/research/paper/69dc786b7d0172140ec789a2.md>)

Recorded evaluation configuration: {"Type":"Base"}. This record does not assert independent reproduction.

### AutoGLM-VLM

HR: 3.58. Result ID: 69dcb29e47f34ce924c3db0c.

[Reporting paper](<https://www.sota2.com/research/paper/69dc786b7d0172140ec789a2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75921e209131cea68b5e.md>)

Recorded evaluation configuration: {"Type":"Base"}. This record does not assert independent reproduction.

### AutoGLM

HR: 4.3. Result ID: 69dcb29e47f34ce924c3db0d.

[Reporting paper](<https://www.sota2.com/research/paper/69dc786b7d0172140ec789a2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75921e209131cea68b5e.md>)

Recorded evaluation configuration: {"Safety Layer":"Prompt"}. This record does not assert independent reproduction.

### AutoGLM

HR: 4.3. Result ID: 69dcb29e47f34ce924c3db0f.

[Reporting paper](<https://www.sota2.com/research/paper/69dc786b7d0172140ec789a2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75921e209131cea68b5e.md>)

Recorded evaluation configuration: {"Safety Layer":"VLM-as-critic"}. This record does not assert independent reproduction.

### CORA

HR: 4.37. Result ID: 69dcb29e47f34ce924c3db10.

[Reporting paper](<https://www.sota2.com/research/paper/69dc786b7d0172140ec789a2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69dc786b7d0172140ec789a2.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### UI-TARS-1.5

HR: 5.73. Result ID: 69dcb29e47f34ce924c3db0b.

[Reporting paper](<https://www.sota2.com/research/paper/69dc786b7d0172140ec789a2.md>)

Recorded evaluation configuration: {"Type":"Base"}. This record does not assert independent reproduction.

### AutoGLM

HR: 24.37. Result ID: 69dcb29e47f34ce924c3db0e.

[Reporting paper](<https://www.sota2.com/research/paper/69dc786b7d0172140ec789a2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75921e209131cea68b5e.md>)

Recorded evaluation configuration: {"Safety Layer":"Heuristic gate"}. This record does not assert independent reproduction.

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