LM Fight Arena: Benchmarking Large Multimodal Models via Game Competition
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912640399310848 |
|---|---|
| author | Zheng, Yushuo Zhang, Zicheng Min, Xiongkuo Duan, Huiyu Zhai, Guangtao |
| author_facet | Zheng, Yushuo Zhang, Zicheng Min, Xiongkuo Duan, Huiyu Zhai, Guangtao |
| contents | Existing benchmarks for large multimodal models (LMMs) often fail to capture their performance in real-time, adversarial environments. We introduce LM Fight Arena (Large Model Fight Arena), a novel framework that evaluates LMMs by pitting them against each other in the classic fighting game Mortal Kombat II, a task requiring rapid visual understanding and tactical, sequential decision-making. In a controlled tournament, we test six leading open- and closed-source models, where each agent operates controlling the same character to ensure a fair comparison. The models are prompted to interpret game frames and state data to select their next actions. Unlike static evaluations, LM Fight Arena provides a fully automated, reproducible, and objective assessment of an LMM's strategic reasoning capabilities in a dynamic setting. This work introduces a challenging and engaging benchmark that bridges the gap between AI evaluation and interactive entertainment. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_08928 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | LM Fight Arena: Benchmarking Large Multimodal Models via Game Competition Zheng, Yushuo Zhang, Zicheng Min, Xiongkuo Duan, Huiyu Zhai, Guangtao Artificial Intelligence Existing benchmarks for large multimodal models (LMMs) often fail to capture their performance in real-time, adversarial environments. We introduce LM Fight Arena (Large Model Fight Arena), a novel framework that evaluates LMMs by pitting them against each other in the classic fighting game Mortal Kombat II, a task requiring rapid visual understanding and tactical, sequential decision-making. In a controlled tournament, we test six leading open- and closed-source models, where each agent operates controlling the same character to ensure a fair comparison. The models are prompted to interpret game frames and state data to select their next actions. Unlike static evaluations, LM Fight Arena provides a fully automated, reproducible, and objective assessment of an LMM's strategic reasoning capabilities in a dynamic setting. This work introduces a challenging and engaging benchmark that bridges the gap between AI evaluation and interactive entertainment. |
| title | LM Fight Arena: Benchmarking Large Multimodal Models via Game Competition |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2510.08928 |