# Jailbreaking on HarmBench n = 200

Source: [Jailbreaking on HarmBench n = 200](<https://www.sota2.com/research/sota/jailbreaking-on-harmbench-n-200>)

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

Data updated: 2026-07-03T07:26:49.855Z

Evaluation of model susceptibility to jailbreaking attacks using the specific HarmBench subset containing 200 samples, reporting Attack Success Rate (ASR).

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 | Jailbreaking |
| Dataset (including any stated split) | HarmBench n = 200 |
| Metric | ASR |
| Unit | PERCENT |
| Direction | Lower is better |
| Results loaded | 18 of 18 |
| 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

- [ASR](<https://www.sota2.com/research/sota/jailbreaking-on-harmbench-n-200.md?metric=ASR>): Lower is better; unit: PERCENT.

## Recorded results

| Method | ASR | Result date | Report paper |
| --- | --- | --- | --- |
| GCG | 16 | Not recorded | 6a47420e143ebdcacacc5ce8 |
| GCG | 19 | Not recorded | 6a47420e143ebdcacacc5ce8 |
| GCG | 19.5 | Not recorded | 6a47420e143ebdcacacc5ce8 |
| CSRT | 32.5 | Not recorded | 6a47420e143ebdcacacc5ce8 |
| GCG | 41.5 | Not recorded | 6a47420e143ebdcacacc5ce8 |
| CSRT | 49.5 | Not recorded | 6a47420e143ebdcacacc5ce8 |
| CSRT | 60.5 | Not recorded | 6a47420e143ebdcacacc5ce8 |
| CSRT | 66 | Not recorded | 6a47420e143ebdcacacc5ce8 |
| STEER | 66 | Not recorded | 6a47420e143ebdcacacc5ce8 |
| GCG | 73 | Not recorded | 6a47420e143ebdcacacc5ce8 |
| STEER | 76 | Not recorded | 6a47420e143ebdcacacc5ce8 |
| STEER | 76.5 | Not recorded | 6a47420e143ebdcacacc5ce8 |
| CSRT | 78.5 | Not recorded | 6a47420e143ebdcacacc5ce8 |
| CSRT | 81.5 | Not recorded | 6a47420e143ebdcacacc5ce8 |
| GCG | 82.5 | Not recorded | 6a47420e143ebdcacacc5ce8 |
| STEER | 86 | Not recorded | 6a47420e143ebdcacacc5ce8 |
| STEER | 86 | Not recorded | 6a47420e143ebdcacacc5ce8 |
| STEER | 87.5 | Not recorded | 6a47420e143ebdcacacc5ce8 |

### GCG

ASR: 16. Result ID: 6a47643860b88bb33992cc9d.

[Reporting paper](<https://www.sota2.com/research/paper/6a47420e143ebdcacacc5ce8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71861e209131cea51c3b.md>)

Recorded evaluation configuration: {"Target Model":"Qwen3-8B","Iterations":"@8"}. This record does not assert independent reproduction.

### GCG

ASR: 19. Result ID: 6a47643860b88bb33992cc9a.

[Reporting paper](<https://www.sota2.com/research/paper/6a47420e143ebdcacacc5ce8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71861e209131cea51c3b.md>)

Recorded evaluation configuration: {"Target Model":"GLM-4-9B","Iterations":"@8"}. This record does not assert independent reproduction.

### GCG

ASR: 19.5. Result ID: 6a47643860b88bb33992cc94.

[Reporting paper](<https://www.sota2.com/research/paper/6a47420e143ebdcacacc5ce8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71861e209131cea51c3b.md>)

Recorded evaluation configuration: {"Target Model":"Llama-3-8B","Iterations":"@8"}. This record does not assert independent reproduction.

### CSRT

ASR: 32.5. Result ID: 6a47643860b88bb33992cc96.

[Reporting paper](<https://www.sota2.com/research/paper/6a47420e143ebdcacacc5ce8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa795c1e209131cea7d43f.md>)

Recorded evaluation configuration: {"Target Model":"DeepSeek-R1","Iterations":"@8"}. This record does not assert independent reproduction.

### GCG

ASR: 41.5. Result ID: 6a47643860b88bb33992cc97.

[Reporting paper](<https://www.sota2.com/research/paper/6a47420e143ebdcacacc5ce8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71861e209131cea51c3b.md>)

Recorded evaluation configuration: {"Target Model":"DeepSeek-R1","Iterations":"@8"}. This record does not assert independent reproduction.

### CSRT

ASR: 49.5. Result ID: 6a47643860b88bb33992cc9c.

[Reporting paper](<https://www.sota2.com/research/paper/6a47420e143ebdcacacc5ce8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa795c1e209131cea7d43f.md>)

Recorded evaluation configuration: {"Target Model":"Qwen3-8B","Iterations":"@8"}. This record does not assert independent reproduction.

### CSRT

ASR: 60.5. Result ID: 6a47643860b88bb33992cc93.

[Reporting paper](<https://www.sota2.com/research/paper/6a47420e143ebdcacacc5ce8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa795c1e209131cea7d43f.md>)

Recorded evaluation configuration: {"Target Model":"Llama-3-8B","Iterations":"@8"}. This record does not assert independent reproduction.

### CSRT

ASR: 66. Result ID: 6a47643860b88bb33992cc90.

[Reporting paper](<https://www.sota2.com/research/paper/6a47420e143ebdcacacc5ce8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa795c1e209131cea7d43f.md>)

Recorded evaluation configuration: {"Target Model":"Gemma-7B","Iterations":"@8"}. This record does not assert independent reproduction.

### STEER

ASR: 66. Result ID: 6a47643860b88bb33992cc98.

[Reporting paper](<https://www.sota2.com/research/paper/6a47420e143ebdcacacc5ce8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a47420e143ebdcacacc5ce8.md>)

Recorded evaluation configuration: {"Target Model":"DeepSeek-R1","Iterations":"@8"}. This record does not assert independent reproduction.

### GCG

ASR: 73. Result ID: 6a47643860b88bb33992cc91.

[Reporting paper](<https://www.sota2.com/research/paper/6a47420e143ebdcacacc5ce8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71861e209131cea51c3b.md>)

Recorded evaluation configuration: {"Target Model":"Gemma-7B","Iterations":"@8"}. This record does not assert independent reproduction.

### STEER

ASR: 76. Result ID: 6a47643860b88bb33992cc9e.

[Reporting paper](<https://www.sota2.com/research/paper/6a47420e143ebdcacacc5ce8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a47420e143ebdcacacc5ce8.md>)

Recorded evaluation configuration: {"Target Model":"Qwen3-8B","Iterations":"@8"}. This record does not assert independent reproduction.

### STEER

ASR: 76.5. Result ID: 6a47643860b88bb33992cc95.

[Reporting paper](<https://www.sota2.com/research/paper/6a47420e143ebdcacacc5ce8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a47420e143ebdcacacc5ce8.md>)

Recorded evaluation configuration: {"Target Model":"Llama-3-8B","Iterations":"@8"}. This record does not assert independent reproduction.

### CSRT

ASR: 78.5. Result ID: 6a47643860b88bb33992cc8d.

[Reporting paper](<https://www.sota2.com/research/paper/6a47420e143ebdcacacc5ce8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa795c1e209131cea7d43f.md>)

Recorded evaluation configuration: {"Target Model":"Mistral-7B","Iterations":"@8"}. This record does not assert independent reproduction.

### CSRT

ASR: 81.5. Result ID: 6a47643860b88bb33992cc99.

[Reporting paper](<https://www.sota2.com/research/paper/6a47420e143ebdcacacc5ce8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa795c1e209131cea7d43f.md>)

Recorded evaluation configuration: {"Target Model":"GLM-4-9B","Iterations":"@8"}. This record does not assert independent reproduction.

### GCG

ASR: 82.5. Result ID: 6a47643860b88bb33992cc8e.

[Reporting paper](<https://www.sota2.com/research/paper/6a47420e143ebdcacacc5ce8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71861e209131cea51c3b.md>)

Recorded evaluation configuration: {"Target Model":"Mistral-7B","Iterations":"@8"}. This record does not assert independent reproduction.

### STEER

ASR: 86. Result ID: 6a47643860b88bb33992cc92.

[Reporting paper](<https://www.sota2.com/research/paper/6a47420e143ebdcacacc5ce8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a47420e143ebdcacacc5ce8.md>)

Recorded evaluation configuration: {"Target Model":"Gemma-7B","Iterations":"@8"}. This record does not assert independent reproduction.

### STEER

ASR: 86. Result ID: 6a47643860b88bb33992cc9b.

[Reporting paper](<https://www.sota2.com/research/paper/6a47420e143ebdcacacc5ce8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a47420e143ebdcacacc5ce8.md>)

Recorded evaluation configuration: {"Target Model":"GLM-4-9B","Iterations":"@8"}. This record does not assert independent reproduction.

### STEER

ASR: 87.5. Result ID: 6a47643860b88bb33992cc8f.

[Reporting paper](<https://www.sota2.com/research/paper/6a47420e143ebdcacacc5ce8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a47420e143ebdcacacc5ce8.md>)

Recorded evaluation configuration: {"Target Model":"Mistral-7B","Iterations":"@8"}. This record does not assert independent reproduction.

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