Scaling Test-Time Compute to Achieve IOI Gold Medal with Open-Weight Models
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_ | 1866914473008168960 |
|---|---|
| author | Samadi, Mehrzad Ficek, Aleksander Narenthiran, Sean Jain, Siddhartha Ahmad, Wasi Uddin Majumdar, Somshubra Noroozi, Vahid Ginsburg, Boris |
| author_facet | Samadi, Mehrzad Ficek, Aleksander Narenthiran, Sean Jain, Siddhartha Ahmad, Wasi Uddin Majumdar, Somshubra Noroozi, Vahid Ginsburg, Boris |
| contents | Competitive programming has become a rigorous benchmark for evaluating the reasoning and problem-solving capabilities of large language models (LLMs). The International Olympiad in Informatics (IOI) stands out as one of the most prestigious annual competitions in competitive programming and has become a key benchmark for comparing human and AI-level programming ability. While several proprietary models have been claimed to achieve gold medal-level performance at the IOI, often with undisclosed methods, achieving comparable results with open-weight models remains a significant challenge. In this paper, we present GenCluster, a scalable and reproducible test-time compute framework that attains IOI gold-level performance using open-weight models. It combines large-scale generation, behavioral clustering, ranking, and a round-robin submission strategy to efficiently explore diverse solution spaces under limited validation budgets. Our experiments show that the performance of our proposed approach scales consistently with available compute, narrowing the gap between open and closed systems. Notably, we will show that GenCluster can achieve a gold medal at IOI 2025 for the first time with an open-weight model gpt-oss-120b, setting a new benchmark for transparent and reproducible evaluation of reasoning in LLMs |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_14232 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Scaling Test-Time Compute to Achieve IOI Gold Medal with Open-Weight Models Samadi, Mehrzad Ficek, Aleksander Narenthiran, Sean Jain, Siddhartha Ahmad, Wasi Uddin Majumdar, Somshubra Noroozi, Vahid Ginsburg, Boris Machine Learning Artificial Intelligence Computation and Language Competitive programming has become a rigorous benchmark for evaluating the reasoning and problem-solving capabilities of large language models (LLMs). The International Olympiad in Informatics (IOI) stands out as one of the most prestigious annual competitions in competitive programming and has become a key benchmark for comparing human and AI-level programming ability. While several proprietary models have been claimed to achieve gold medal-level performance at the IOI, often with undisclosed methods, achieving comparable results with open-weight models remains a significant challenge. In this paper, we present GenCluster, a scalable and reproducible test-time compute framework that attains IOI gold-level performance using open-weight models. It combines large-scale generation, behavioral clustering, ranking, and a round-robin submission strategy to efficiently explore diverse solution spaces under limited validation budgets. Our experiments show that the performance of our proposed approach scales consistently with available compute, narrowing the gap between open and closed systems. Notably, we will show that GenCluster can achieve a gold medal at IOI 2025 for the first time with an open-weight model gpt-oss-120b, setting a new benchmark for transparent and reproducible evaluation of reasoning in LLMs |
| title | Scaling Test-Time Compute to Achieve IOI Gold Medal with Open-Weight Models |
| topic | Machine Learning Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2510.14232 |