# URLs Extraction on CyberThreat-Eval

Source: [URLs Extraction on CyberThreat-Eval](<https://www.sota2.com/research/sota/urls-extraction-on-cyberthreat-eval>)

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

Data updated: 2026-03-11T08:48:51.043Z

Evaluation of model performance on extracting URLs from the CyberThreat-Eval dataset, measured by processing counts and time efficiency.

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 | URLs Extraction |
| Dataset (including any stated split) | CyberThreat-Eval |
| Metric | Average URLs Processed |
| 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

- [Average URLs Processed](<https://www.sota2.com/research/sota/urls-extraction-on-cyberthreat-eval.md?metric=Average%20URLs%20Processed>): Higher is better; unit: SCALAR.

- [Average URLs with Additional Info](<https://www.sota2.com/research/sota/urls-extraction-on-cyberthreat-eval.md?metric=Average%20URLs%20with%20Additional%20Info>): Higher is better; unit: SCALAR.

- [Average Processing Time (s)](<https://www.sota2.com/research/sota/urls-extraction-on-cyberthreat-eval.md?metric=Average%20Processing%20Time%20(s)>): Lower is better; unit: TIME.

## Recorded results

| Method | Average URLs Processed | Result date | Report paper |
| --- | --- | --- | --- |
| GPT-4o | 6.22 | Not recorded | 69b0f72b2d603e6de3e45f51 |
| o3-mini | 4.93 | Not recorded | 69b0f72b2d603e6de3e45f51 |
| GPT-4o (FT) | 1.75 | Not recorded | 69b0f72b2d603e6de3e45f51 |
| GPT-4o-mini (FT) | 1.25 | Not recorded | 69b0f72b2d603e6de3e45f51 |

### GPT-4o

Average URLs Processed: 6.22. Result ID: 69b12c6e6dbb7075b95baa7f.

[Reporting paper](<https://www.sota2.com/research/paper/69b0f72b2d603e6de3e45f51.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75681e209131cea67a98.md>)

Recorded evaluation configuration: {"Fine-tuned":"false"}. This record does not assert independent reproduction.

### o3-mini

Average URLs Processed: 4.93. Result ID: 69b12c6e6dbb7075b95baa80.

[Reporting paper](<https://www.sota2.com/research/paper/69b0f72b2d603e6de3e45f51.md>)

Recorded evaluation configuration: {"Fine-tuned":"false"}. This record does not assert independent reproduction.

### GPT-4o (FT)

Average URLs Processed: 1.75. Result ID: 69b12c6e6dbb7075b95baa81.

[Reporting paper](<https://www.sota2.com/research/paper/69b0f72b2d603e6de3e45f51.md>)

Recorded evaluation configuration: {"Fine-tuned":"true"}. This record does not assert independent reproduction.

### GPT-4o-mini (FT)

Average URLs Processed: 1.25. Result ID: 69b12c6e6dbb7075b95baa82.

[Reporting paper](<https://www.sota2.com/research/paper/69b0f72b2d603e6de3e45f51.md>)

Recorded evaluation configuration: {"Fine-tuned":"true"}. This record does not assert independent reproduction.

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