Hakimi Platform Delivers Effective Speaking Scoring: Gemini Models Show Strong Results

A user on the Linux.do forum shared their personal experience using the Hakimi platform to implement a speaking scoring model. After testing, Google’s Gemini-3-flash-preview and Gemini-3-pro-preview models demonstrated strong accuracy, providing an effective solution for speaking assessment. This discovery highlights the potential of AI technology in language education, offering practical value for both language learners and educators. Three participants in the forum discussed the topic, further validating the feasibility of this method.