Table 13 NCK-Bench score on models’ comparison.
From: Localized large language model TCNNet 9B for Taiwanese networking and cybersecurity
Models | Benchmark score |
|---|---|
gpt-4o | 71.9322 |
gpt-3.5-turbo | 68.1923 |
TCNNet-9B | 55.8192 |
gemini-1.5-pro | 50.1721 |
gemini-1.0-pro | 45.0921 |
Yi-1.5-9B | 40.1330 |
