# Jailbreaking on JBB n = 100

Source: [Jailbreaking on JBB n = 100](<https://www.sota2.com/research/sota/jailbreaking-on-jbb-n-100>)

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

Data updated: 2026-07-03T07:26:49.835Z

Evaluation of model susceptibility to jailbreaking prompts using the JBB dataset subset of size 100, measured by 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) | JBB n = 100 |
| Metric | ASR |
| Unit | PERCENT |
| Direction | Higher 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-jbb-n-100.md?metric=ASR>): Higher is better; unit: PERCENT.

## Recorded results

| Method | ASR | Result date | Report paper |
| --- | --- | --- | --- |
| STEER | 93 | Not recorded | 6a47420e143ebdcacacc5ce8 |
| STEER | 93 | Not recorded | 6a47420e143ebdcacacc5ce8 |
| GCG | 92 | Not recorded | 6a47420e143ebdcacacc5ce8 |
| STEER | 92 | Not recorded | 6a47420e143ebdcacacc5ce8 |
| CSRT | 90 | Not recorded | 6a47420e143ebdcacacc5ce8 |
| GCG | 89 | Not recorded | 6a47420e143ebdcacacc5ce8 |
| CSRT | 89 | Not recorded | 6a47420e143ebdcacacc5ce8 |
| CSRT | 88 | Not recorded | 6a47420e143ebdcacacc5ce8 |
| STEER | 85 | Not recorded | 6a47420e143ebdcacacc5ce8 |
| STEER | 83 | Not recorded | 6a47420e143ebdcacacc5ce8 |
| STEER | 80 | Not recorded | 6a47420e143ebdcacacc5ce8 |
| CSRT | 55 | Not recorded | 6a47420e143ebdcacacc5ce8 |
| GCG | 53 | Not recorded | 6a47420e143ebdcacacc5ce8 |
| GCG | 47 | Not recorded | 6a47420e143ebdcacacc5ce8 |
| CSRT | 47 | Not recorded | 6a47420e143ebdcacacc5ce8 |
| CSRT | 44 | Not recorded | 6a47420e143ebdcacacc5ce8 |
| GCG | 41 | Not recorded | 6a47420e143ebdcacacc5ce8 |
| GCG | 39 | Not recorded | 6a47420e143ebdcacacc5ce8 |

### STEER

ASR: 93. Result ID: 6a47643860b88bb33992cc80.

[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: 93. Result ID: 6a47643860b88bb33992cc89.

[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.

### GCG

ASR: 92. Result ID: 6a47643860b88bb33992cc7c.

[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: 92. Result ID: 6a47643860b88bb33992cc7d.

[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.

### CSRT

ASR: 90. Result ID: 6a47643860b88bb33992cc7b.

[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.

### GCG

ASR: 89. Result ID: 6a47643860b88bb33992cc7f.

[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.

### CSRT

ASR: 89. Result ID: 6a47643860b88bb33992cc87.

[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.

### CSRT

ASR: 88. Result ID: 6a47643860b88bb33992cc7e.

[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: 85. Result ID: 6a47643860b88bb33992cc8c.

[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: 83. Result ID: 6a47643860b88bb33992cc83.

[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.

### STEER

ASR: 80. Result ID: 6a47643860b88bb33992cc86.

[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.

### CSRT

ASR: 55. Result ID: 6a47643860b88bb33992cc81.

[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.

### GCG

ASR: 53. Result ID: 6a47643860b88bb33992cc8b.

[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: 47. Result ID: 6a47643860b88bb33992cc85.

[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: 47. Result ID: 6a47643860b88bb33992cc8a.

[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: 44. Result ID: 6a47643860b88bb33992cc84.

[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. Result ID: 6a47643860b88bb33992cc82.

[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.

### GCG

ASR: 39. Result ID: 6a47643860b88bb33992cc88.

[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.

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