ComBench: A Benchmark for Rigorous Proof Reasoning and Constructive Realization in Olympiad-Level Combinatorics
Quick Answer
ComBench is a new benchmark for evaluating combinatorial reasoning in large language models, revealing a performance gap in Olympiad-level problems.
Quick Take
The strongest model, Kimi-K2.6, scores 65.4% overall, while GPT-5.5 excels in analysis but not in construction tasks. This highlights distinct capabilities in rigorous proof reasoning versus constructive realization.
Key Points
- ComBench includes 100 human-annotated Olympiad-level combinatorial problems.
- Problems are divided into analysis-centric and construction-centric categories.
- Evaluation combines proof grading with deterministic construction verification.
- Kimi-K2.6 outperforms GPT-5.5 in construction tasks but lags in proof grading.
- Existence and Construction problems are consistently the hardest across models.
Paper Resources
Source Excerpt
arXiv:2606. 10479v1 Announce Type: new Abstract: Combinatorics is central to Olympiad-level mathematical problem solving, requiring deep discrete reasoning, creative constructions, and rigorous structural insight. Recent evidence suggests that even today's strongest frontier models remain uneven on Olympiad combinatorics, revealing a gap in creative mathematical reasoning.
We introduce ComBench, an Olympiad-level combinatorics benchmark for evaluating and diagnosing the combinatorial reasoning capabilities of . …
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.AI
See more →AINTMA: Agentic AI Architecture for Autonomous Test Management with Generative Intelligence, Secure Cloud Communication and Adaptive Quality Analytics
AINTMA, an autonomous test management architecture utilizing six specialized AI agents, achieves 88.4% test prioritization accuracy and reduces defect escape rates from 8.3% to 2.1%. The system demonstrates a 340% ROI within nine months, showcasing the potential of agentic AI in enhancing software quality management in cloud environments.