open-r1

OlympicCoder-7B is an open-source language model fine-tuned on the CodeForces-CoTs dataset, consisting of nearly 100,000 high-quality chain-of-thought examples from competitive programming contexts. Optimized specifically for olympiad-level coding problems, this model demonstrates strong chain-of-thought reasoning and competitive code generation capabilities, achieving performance competitive with frontier closed-source models on tasks from the IOI 2024 and similar coding contests.

OlympicCoder-32B is a high-performing open-source model fine-tuned using the CodeForces-CoTs dataset, containing approximately 100,000 chain-of-thought programming samples. It excels at complex competitive programming benchmarks, such as IOI 2024 and Codeforces-style challenges, frequently surpassing state-of-the-art closed-source models. OlympicCoder-32B provides advanced reasoning, coherent multi-step problem-solving, and robust code generation capabilities, demonstrating significant potential for olympiad-level competitive programming applications.