Table 12 TNCK-Bench score for model comparison.
From: Localized large language model TCNNet 9B for Taiwanese networking and cybersecurity
Models | Benchmark score |
|---|---|
gpt-4o | 67.7939 |
gpt-3.5-turbo | 66.3969 |
TCNNet-9B | 53.4782 |
gemini-1.5-pro | 50.0611 |
gemini-1.0-pro | 44.2137 |
Yi-1.5-9B | 38.8554 |
