Table 2.

Accuracy of large language models in Practical Skills.

Year	GPT-3.5	GPT-4.0	GPT-4o	Copilot	ERNIE Bot-3.5	SPARK	Qwen-2.5
2023	0.550	0.775	0.833	0.792	0.775	0.758	0.908
2022	0.467	0.692	0.800	0.792	0.792	0.675	0.850
2021	0.467	0.708	0.850	0.667	0.750	0.567	0.942
2020	0.475	0.642	0.783	0.592	0.800	0.700	0.933
2019	0.483	0.658	0.783	0.458	0.767	0.592	0.883
Overall	0.488	0.695	0.810	0.660	0.777	0.658	0.903