# Cyber-Threat Intelligence Prediction on LLM-CTI (Prediction)

Source: [Cyber-Threat Intelligence Prediction on LLM-CTI (Prediction)](<https://www.sota2.com/research/sota/cyber-threat-intelligence-prediction-on-llm-cti-prediction>)

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

Data updated: 2026-05-26T07:09:35.587Z

Evaluation of model performance on the LLM-CTI (Prediction) dataset for the task of Cyber-Threat Intelligence Prediction, utilizing metrics such as AUC, BLEU, and Accuracy across specific prediction dimensions like Exploit Likelihood and Campaign Escalation.

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 | Cyber-Threat Intelligence Prediction |
| Dataset (including any stated split) | LLM-CTI (Prediction) |
| Metric | Exploit Likelihood (AUC) |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 15 of 15 |
| 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

- [Exploit Likelihood (AUC)](<https://www.sota2.com/research/sota/cyber-threat-intelligence-prediction-on-llm-cti-prediction.md?metric=Exploit%20Likelihood%20(AUC)>): Higher is better; unit: SCALAR.

- [Impact Forecast (BLEU)](<https://www.sota2.com/research/sota/cyber-threat-intelligence-prediction-on-llm-cti-prediction.md?metric=Impact%20Forecast%20(BLEU)>): Higher is better; unit: SCALAR.

- [Accuracy (Target Sector)](<https://www.sota2.com/research/sota/cyber-threat-intelligence-prediction-on-llm-cti-prediction.md?metric=Accuracy%20(Target%20Sector)>): Higher is better; unit: PERCENT.

- [Campaign Escalation (AUC)](<https://www.sota2.com/research/sota/cyber-threat-intelligence-prediction-on-llm-cti-prediction.md?metric=Campaign%20Escalation%20(AUC)>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Exploit Likelihood (AUC) | Result date | Report paper |
| --- | --- | --- | --- |
| LL70 | 0.856 | Not recorded | 68fa7bc11e209131cea8a354 |
| G5 | 0.821 | Not recorded | 68fa7bc11e209131cea8a354 |
| Go4 | 0.806 | Not recorded | 68fa7bc11e209131cea8a354 |
| CLD | 0.792 | Not recorded | 68fa7bc11e209131cea8a354 |
| GEM | 0.771 | Not recorded | 68fa7bc11e209131cea8a354 |
| CBS | 0.764 | Not recorded | 68fa7bc11e209131cea8a354 |
| DHT | 0.759 | Not recorded | 68fa7bc11e209131cea8a354 |
| MIX | 0.742 | Not recorded | 68fa7bc11e209131cea8a354 |
| ZYS | 0.742 | Not recorded | 68fa7bc11e209131cea8a354 |
| GRK | 0.714 | Not recorded | 68fa7bc11e209131cea8a354 |
| CB0 | 0.703 | Not recorded | 68fa7bc11e209131cea8a354 |
| SPT | 0.653 | Not recorded | 68fa7bc11e209131cea8a354 |
| QWN | 0.629 | Not recorded | 68fa7bc11e209131cea8a354 |
| LLY | 0.559 | Not recorded | 68fa7bc11e209131cea8a354 |
| FSC | 0.519 | Not recorded | 68fa7bc11e209131cea8a354 |

### LL70

Exploit Likelihood (AUC): 0.856. Result ID: 6a154714fbc373592c0c271d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bc11e209131cea8a354.md>)

Recorded evaluation configuration: {"Model Category":"Industry-leading, general-purpose"}. This record does not assert independent reproduction.

### G5

Exploit Likelihood (AUC): 0.821. Result ID: 6a154714fbc373592c0c2719.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bc11e209131cea8a354.md>)

Recorded evaluation configuration: {"Model Category":"Industry-leading, general-purpose"}. This record does not assert independent reproduction.

### Go4

Exploit Likelihood (AUC): 0.806. Result ID: 6a154714fbc373592c0c271a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bc11e209131cea8a354.md>)

Recorded evaluation configuration: {"Model Category":"Industry-leading, general-purpose"}. This record does not assert independent reproduction.

### CLD

Exploit Likelihood (AUC): 0.792. Result ID: 6a154714fbc373592c0c271b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bc11e209131cea8a354.md>)

Recorded evaluation configuration: {"Model Category":"Industry-leading, general-purpose"}. This record does not assert independent reproduction.

### GEM

Exploit Likelihood (AUC): 0.771. Result ID: 6a154714fbc373592c0c271c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bc11e209131cea8a354.md>)

Recorded evaluation configuration: {"Model Category":"Industry-leading, general-purpose"}. This record does not assert independent reproduction.

### CBS

Exploit Likelihood (AUC): 0.764. Result ID: 6a154714fbc373592c0c2725.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bc11e209131cea8a354.md>)

Recorded evaluation configuration: {"Model Category":"Cybersecurity-specialized"}. This record does not assert independent reproduction.

### DHT

Exploit Likelihood (AUC): 0.759. Result ID: 6a154714fbc373592c0c2727.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bc11e209131cea8a354.md>)

Recorded evaluation configuration: {"Model Category":"Cybersecurity-specialized"}. This record does not assert independent reproduction.

### MIX

Exploit Likelihood (AUC): 0.742. Result ID: 6a154714fbc373592c0c271e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bc11e209131cea8a354.md>)

Recorded evaluation configuration: {"Model Category":"Industry-leading, general-purpose"}. This record does not assert independent reproduction.

### ZYS

Exploit Likelihood (AUC): 0.742. Result ID: 6a154714fbc373592c0c2723.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bc11e209131cea8a354.md>)

Recorded evaluation configuration: {"Model Category":"Cybersecurity-specialized"}. This record does not assert independent reproduction.

### GRK

Exploit Likelihood (AUC): 0.714. Result ID: 6a154714fbc373592c0c2720.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bc11e209131cea8a354.md>)

Recorded evaluation configuration: {"Model Category":"Industry-leading, general-purpose"}. This record does not assert independent reproduction.

### CB0

Exploit Likelihood (AUC): 0.703. Result ID: 6a154714fbc373592c0c2722.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bc11e209131cea8a354.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7ae51e209131cea85c05.md>)

Recorded evaluation configuration: {"Model Category":"Cybersecurity-specialized"}. This record does not assert independent reproduction.

### SPT

Exploit Likelihood (AUC): 0.653. Result ID: 6a154714fbc373592c0c2726.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bc11e209131cea8a354.md>)

Recorded evaluation configuration: {"Model Category":"Cybersecurity-specialized"}. This record does not assert independent reproduction.

### QWN

Exploit Likelihood (AUC): 0.629. Result ID: 6a154714fbc373592c0c271f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bc11e209131cea8a354.md>)

Recorded evaluation configuration: {"Model Category":"Industry-leading, general-purpose"}. This record does not assert independent reproduction.

### LLY

Exploit Likelihood (AUC): 0.559. Result ID: 6a154714fbc373592c0c2724.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bc11e209131cea8a354.md>)

Recorded evaluation configuration: {"Model Category":"Cybersecurity-specialized"}. This record does not assert independent reproduction.

### FSC

Exploit Likelihood (AUC): 0.519. Result ID: 6a154714fbc373592c0c2721.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bc11e209131cea8a354.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a521e209131cea82724.md>)

Recorded evaluation configuration: {"Model Category":"Cybersecurity-specialized"}. This record does not assert independent reproduction.

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