Cybersecurity Knowledge Evaluation on MMLU Security
93.2Accuracy
GPT-5
Updated 4d ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2026.01 | 93.2 | 0.007 | |
2026.01 | 88.4 | 0.014 | |
2026.01 | 88 | 0.019 | |
2026.01 | 87.2 | 0.007 | |
2026.01 | 87 | 0.009 | |
2026.01 | 87 | 0.011 | |
2026.01 | 86.4 | 0.017 | |
2026.01 | 85.8 | 0.017 | |
2026.01 | 84.6 | 0.014 | |
2026.01 | 84.4 | 0.01 | |
2026.01 | 83.6 | 0.016 | |
| 83.4 | 0.027 | ||
2026.01 | 78.2 | 0.023 | |
2026.01 | 77 | 0.026 | |
2026.01 | 76.8 | 0.01 | |
2026.01 | 76.2 | 0.029 | |
2026.01 | 66.6 | 0.022 |