Abstract
Characterizing LLM reasoning remains an open challenge, as many existing benchmarks isolate specific reasoning skills, rely on external knowledge, or are costly to extend. We introduce PetriBench, a compact, fully self-contained, and scalable benchmark for evaluating LLM reasoning over dynamic state spaces using Petri nets, a mature formalism for modeling real-world concurrent and distributed systems. PetriBench organizes reasoning into four task families varying by scope and temporal horizon, with Easy, Medium, and Hard levels generated by increasing structural complexity and evaluated against exact ground truth. Across a diverse set of proprietary and open-weight models, accuracy decreases consistently with difficulty, while harder instances expose increasingly distinct task-specific capability profiles. Additional analyses show that test-time compute improves performance but interacts differently with different reasoning tasks, and that procedural generation yields smooth scaling with structural complexity. Together, these results show that PetriBench provides a unified and extensible setting for probing the strengths, limits, and scaling behavior of LLM reasoning.
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Koussios, P., Jäger, B., Yao, J. H., Sridhar, A., Xiang, V., & Li, C. (2026). PetriBench: Benchmarking LLM Reasoning over Dynamic State Spaces. https://omanscience.com/en/articles/petribench-benchmarking-llm-reasoning-over-dynamic-state-spaces
MLA 9
Koussios, Pyrros, et al. "PetriBench: Benchmarking LLM Reasoning over Dynamic State Spaces." https://omanscience.com/en/articles/petribench-benchmarking-llm-reasoning-over-dynamic-state-spaces.
Chicago (author–date)
Koussios, Pyrros, Benjamin Jäger, John Hua Yao, Ajay Sridhar, Violet Xiang, and Chenhao Li. 2026. "PetriBench: Benchmarking LLM Reasoning over Dynamic State Spaces." https://omanscience.com/en/articles/petribench-benchmarking-llm-reasoning-over-dynamic-state-spaces.
Harvard
Koussios, P., Jäger, B., Yao, J. H., Sridhar, A., Xiang, V. and Li, C. (2026) 'PetriBench: Benchmarking LLM Reasoning over Dynamic State Spaces', Available at: https://omanscience.com/en/articles/petribench-benchmarking-llm-reasoning-over-dynamic-state-spaces.
Vancouver
Koussios P, Jäger B, Yao JH, Sridhar A, Xiang V, Li C. PetriBench: Benchmarking LLM Reasoning over Dynamic State Spaces. https://omanscience.com/en/articles/petribench-benchmarking-llm-reasoning-over-dynamic-state-spaces
IEEE
P. Koussios, B. Jäger, J. H. Yao, A. Sridhar, V. Xiang, and C. Li, "PetriBench: Benchmarking LLM Reasoning over Dynamic State Spaces," https://omanscience.com/en/articles/petribench-benchmarking-llm-reasoning-over-dynamic-state-spaces.