FrontierCS: Evolving Challenges for Evolving Intelligence

TL;DR

FrontierCS is a comprehensive benchmark of 156 open-ended computer science problems designed to evaluate models' ability to generate high-quality solutions in complex, unknown- optimality tasks, highlighting significant gaps between AI models and human experts.

Contribution

The paper introduces FrontierCS, a novel benchmark with expert-reviewed problems and objective evaluation, focusing on open-ended, complex tasks where solutions are not predefined.

Findings

Models lag behind human experts in solving complex problems.

Increasing reasoning budgets does not significantly improve model performance.

Models tend to produce workable code rather than optimal algorithms.

Abstract

We introduce FrontierCS, a benchmark of 156 open-ended problems across diverse areas of computer science, designed and reviewed by experts, including CS PhDs and top-tier competitive programming participants and problem setters. Unlike existing benchmarks that focus on tasks with known optimal solutions, FrontierCS targets problems where the optimal solution is unknown, but the quality of a solution can be objectively evaluated. Models solve these tasks by implementing executable programs rather than outputting a direct answer. FrontierCS includes algorithmic problems, which are often NP-hard variants of competitive programming problems with objective partial scoring, and research problems with the same property. For each problem we provide an expert reference solution and an automatic evaluator. Combining open-ended design, measurable progress, and expert curation, FrontierCS provides a benchmark at the frontier of computer-science difficulty. Empirically, we find that frontier reasoning models still lag far behind human experts on both the algorithmic and research tracks, that increasing reasoning budgets alone does not close this gap, and that models often over-optimize for generating merely workable code instead of discovering high-quality algorithms and system designs.