Comparative analysis of large language models for generating dialogues in the gaming industry

The relevance of the study is due to the growing demands on the quality and variability of content in the modern gaming industry, in particular, to the replicas of non-player characters (NPCs), whose traditional writing methods may not fully ensure variability and replayability. This article aims to identify the most appropriate large language model (LLM) for generating NPC replicas by comparative analysis according to a number of criteria. The leading research method is a comparative analysis of two groups of models: LLM with a large number of parameters (DeepSeek-V3.2, Qwen 3-Max, GigaChat 2 Max) provided via API\Web services and models with a small number of parameters (DeepSeek-R1:14b, Qwen 3:14b, Phi4:14b) running on a personal computer. The paper presents criteria for evaluating the quality of responses and technical characteristics, shows the testing algorithm and the structure of the request. An integrated performance indicator was introduced for a comprehensive assessment of models, taking into account several key criteria for the quality of responses. As a result, the preferred LLMs were identified in both groups: the GigaChat 2 Max model showed the best compliance with the rules of generation and is recommended for use for Russian-language game projects. Among the second group the DeepSeek-R1:14b model showed the best results. The materials of the article are of practical value to developers in the gaming industry, providing sound recommendations for integrating LLM to automate the creation of NPC replicas.

1. Kupalov G.S. Possibilities of using video games in education. Bulletin of Pedagogical Sciences. 2021;(3):151–155. (In Russ.).

2. Kyzmina A.P., Kuregyan A.L., Percevaya E.A. The use of computer video games as an independent work tool to improve the communicative skills of english language learners in non-linguistic higher education institutions. Concept. 2025;(8):185–200. (In Russ.). https://doi.org/10.24412/2304-120X-2025-11159

3. Nalesnaya Ya.A., Lebedev E.P. Should Esports be considered a real profession today? In: Scientific dialogue: questions of philosophy, sociology, history, political science: Proceedings of the XIII International Scientific Conference, 01 April 2018, Saint Petersburg, Russia. Izd. TsNK MNIF "Obshchestvennaya nauka"; 2018. P. 8–13. (In Russ.). https://doi.org/10.18411/spc-01-04-2018-02

4. Demin K.A., Pushkareva I.N., Tagiltseva Yu.R. Military genre computer games as an element of propaganda in information warfare between Russia and the USA. Political Linguistics. 2016;(5):110–116. (In Russ.).

5. Kirichenko D.V., Galaguzova Yu.N. Gamification in the work of a secondary school teacher: Experience and prospects. Pedagogical Education in Russia. 2022;(3):13–19. (In Russ.).

6. Abrosimova T.Yu. Comparative characteristics of demand for video games on the basis of various game clients. In: Fundamental scientific research: Proceedings of the International research competition, 29 February 2020, Saint Petersburg, Russia. ESMC "Multidisciplinary research"; 2020. P. 28–31. (In Russ.).

7. Gobozov V.V. Trends and modern technologies for creating game content. International Journal of Humanities and Natural Sciences. 2025;(7-2):224–230. (In Russ.). https://doi.org/10.24412/2500-1000-2025-7-2-224-230

8. Kumaran V., Rowe J., Mott B., Lester J. SceneCraft: Automating Interactive Narrative Scene Generation in Digital Games with Large Language Models. In: Proceedings of the Nineteenth AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, 08–12 October 2023, Salt Lake City, UT, USA. AAAI Press; 2023. P. 86–96. https://doi.org/10.1609/aiide.v19i1.27504

9. Gallotta R., Todd G., Zammit M., et al. Large Language Models and Games: A Survey and Roadmap. IEEE Transactions on Games. 2024;1–18. https://doi.org/10.1109/TG.2024.3461510

10. Lyubimov I.I., Manaev C.I., Melnikov A.N., Sultanov N.Z. Methodological basis of optimization prosess for collection and transportation of domestic solid waste. Intellect. Innovations. Investments. 2011;(2):35–40. (In Russ.).