# IoC Extraction on CyberThreat-Eval

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

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

Data updated: 2026-03-11T08:48:51.067Z

Evaluation of Indicator of Compromise (IoC) Extraction performance on the CyberThreat-Eval dataset, measured by Precision, Time, and Tokens.

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 | IoC Extraction |
| Dataset (including any stated split) | CyberThreat-Eval |
| Metric | Precision |
| Unit | PERCENT |
| 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

- [Precision](<https://www.sota2.com/research/sota/ioc-extraction-on-cyberthreat-eval.md?metric=Precision>): Higher is better; unit: PERCENT.

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

- [Tokens](<https://www.sota2.com/research/sota/ioc-extraction-on-cyberthreat-eval.md?metric=Tokens>): Lower is better; unit: SCALAR.

## Recorded results

| Method | Precision | Result date | Report paper |
| --- | --- | --- | --- |
| GPT-4o (FT) | 88.46 | Not recorded | 69b0f72b2d603e6de3e45f51 |
| o3-mini | 85.03 | Not recorded | 69b0f72b2d603e6de3e45f51 |
| GPT-4o | 82.4 | Not recorded | 69b0f72b2d603e6de3e45f51 |
| GPT-4o-mini (FT) | 69.44 | Not recorded | 69b0f72b2d603e6de3e45f51 |

### GPT-4o (FT)

Precision: 88.46. Result ID: 69b12c6e6dbb7075b95baa85.

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

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

### o3-mini

Precision: 85.03. Result ID: 69b12c6e6dbb7075b95baa84.

[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

Precision: 82.4. Result ID: 69b12c6e6dbb7075b95baa83.

[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.

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

Precision: 69.44. Result ID: 69b12c6e6dbb7075b95baa86.

[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.