# Pentesting Strategy Generation on Pentesting Scenarios (test)

Source: [Pentesting Strategy Generation on Pentesting Scenarios (test)](<https://www.sota2.com/research/sota/pentesting-strategy-generation-on-pentesting-scenarios-test>)

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

Data updated: 2026-05-07T08:36:16.700Z

Evaluation of model performance in generating effective penetration testing strategies using the specified test scenarios dataset.

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 | Pentesting Strategy Generation |
| Dataset (including any stated split) | Pentesting Scenarios (test) |
| Metric | Strategy Success Rate |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 11 of 11 |
| 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

- [Strategy Success Rate](<https://www.sota2.com/research/sota/pentesting-strategy-generation-on-pentesting-scenarios-test.md?metric=Strategy%20Success%20Rate>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Strategy Success Rate | Result date | Report paper |
| --- | --- | --- | --- |
| Qwen-3-14B-GRPO | 73 | Not recorded | 69fc1cac5497b3b670c88619 |
| Claude 4.5 Sonnet | 65 | Not recorded | 69fc1cac5497b3b670c88619 |
| GPT-5 | 62 | Not recorded | 69fc1cac5497b3b670c88619 |
| GPT 4.1 | 60 | Not recorded | 69fc1cac5497b3b670c88619 |
| Claude 3 Haiku | 54 | Not recorded | 69fc1cac5497b3b670c88619 |
| GPT-4o-mini | 52 | Not recorded | 69fc1cac5497b3b670c88619 |
| Gemini 2.5 Flash | 45 | Not recorded | 69fc1cac5497b3b670c88619 |
| Gemini 2.0 Flash | 40 | Not recorded | 69fc1cac5497b3b670c88619 |
| LLaMA-3.1-8B | 40 | Not recorded | 69fc1cac5497b3b670c88619 |
| Qwen-3-14B | 39 | Not recorded | 69fc1cac5497b3b670c88619 |
| GPT-3.5-turbo | 36 | Not recorded | 69fc1cac5497b3b670c88619 |

### Qwen-3-14B-GRPO

Strategy Success Rate: 73. Result ID: 69fc4dae47f34ce924df0257.

[Reporting paper](<https://www.sota2.com/research/paper/69fc1cac5497b3b670c88619.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69fc1cac5497b3b670c88619.md>)

Recorded evaluation configuration: {"Parameters":"14B","Optimization":"GRPO"}. This record does not assert independent reproduction.

### Claude 4.5 Sonnet

Strategy Success Rate: 65. Result ID: 69fc4dae47f34ce924df024e.

[Reporting paper](<https://www.sota2.com/research/paper/69fc1cac5497b3b670c88619.md>)

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

### GPT-5

Strategy Success Rate: 62. Result ID: 69fc4dae47f34ce924df0254.

[Reporting paper](<https://www.sota2.com/research/paper/69fc1cac5497b3b670c88619.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa680c1e209131cea19d53.md>)

[Implementation](<https://github.com/openai/gpt-3/blob/master/overlap_frequency.md>)

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

### GPT 4.1

Strategy Success Rate: 60. Result ID: 69fc4dae47f34ce924df0252.

[Reporting paper](<https://www.sota2.com/research/paper/69fc1cac5497b3b670c88619.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa680c1e209131cea19d53.md>)

[Implementation](<https://github.com/openai/gpt-3/blob/master/overlap_frequency.md>)

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

### Claude 3 Haiku

Strategy Success Rate: 54. Result ID: 69fc4dae47f34ce924df024d.

[Reporting paper](<https://www.sota2.com/research/paper/69fc1cac5497b3b670c88619.md>)

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

### GPT-4o-mini

Strategy Success Rate: 52. Result ID: 69fc4dae47f34ce924df0253.

[Reporting paper](<https://www.sota2.com/research/paper/69fc1cac5497b3b670c88619.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa680c1e209131cea19d53.md>)

[Implementation](<https://github.com/openai/gpt-3/blob/master/overlap_frequency.md>)

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

### Gemini 2.5 Flash

Strategy Success Rate: 45. Result ID: 69fc4dae47f34ce924df0250.

[Reporting paper](<https://www.sota2.com/research/paper/69fc1cac5497b3b670c88619.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78731e209131cea78622.md>)

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

### Gemini 2.0 Flash

Strategy Success Rate: 40. Result ID: 69fc4dae47f34ce924df024f.

[Reporting paper](<https://www.sota2.com/research/paper/69fc1cac5497b3b670c88619.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78731e209131cea78622.md>)

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

### LLaMA-3.1-8B

Strategy Success Rate: 40. Result ID: 69fc4dae47f34ce924df0255.

[Reporting paper](<https://www.sota2.com/research/paper/69fc1cac5497b3b670c88619.md>)

Recorded evaluation configuration: {"Parameters":"8B"}. This record does not assert independent reproduction.

### Qwen-3-14B

Strategy Success Rate: 39. Result ID: 69fc4dae47f34ce924df0256.

[Reporting paper](<https://www.sota2.com/research/paper/69fc1cac5497b3b670c88619.md>)

Recorded evaluation configuration: {"Parameters":"14B"}. This record does not assert independent reproduction.

### GPT-3.5-turbo

Strategy Success Rate: 36. Result ID: 69fc4dae47f34ce924df0251.

[Reporting paper](<https://www.sota2.com/research/paper/69fc1cac5497b3b670c88619.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa680c1e209131cea19d53.md>)

[Implementation](<https://github.com/openai/gpt-3/blob/master/overlap_frequency.md>)

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

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