Content: Threat Actor on CyberThreat-Eval
3.964Relevanceo3-mini
Evaluation Results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
| o3-miniFine-tuned=false2026.03 | 3.964 | 3.656 | 3.165 | 4.753 | 4.731 | 2.968 | |
| GPT-4o (FT)Fine-tuned=true2026.03 | 3.964 | 3.655 | 3.165 | 4.752 | 4.731 | 2.967 | |
| GPT-4o-mini (FT)Fine-tuned=true2026.03 | 2.475 | 2.405 | 1.755 | 3.699 | 3.405 | 1.832 | |
| GPT-4oFine-tuned=false2026.03 | 1.547 | 1.528 | 1.145 | 2.019 | 1.734 | 1.14 |