BigO(Bench) - Can LLMs Generate Code with Controlled Time and Space Complexity?

ICLR 2026 Conference Submission20453 Authors

Keywords: Computational Complexity, Program Synthesis, Code Generation, Competitive Programming, LLMs, Large Language Model, Benchmark

TL;DR: BigO(Bench) assesses the capacity of Large Language Models (LLMs) to comprehend time-space computational complexity of input or generated code.

Abstract: We introduce BigO(Bench), a novel coding benchmark designed to evaluate the capabilities of generative language models in understanding and generating code with specified time and space complexities. This benchmark addresses the gap in current evaluations that often overlook the ability of models to comprehend and produce code constrained by computational complexity. BigO(Bench) includes tooling to infer the algorithmic complexity of any Python function from profiling measurements, including human- or LLM-generated solutions. BigO(Bench) also includes a set of 3,105 coding problems and 1,190,250 solutions from Code Contests annotated with inferred (synthetic) time and space complexity labels from the complexity framework, as well as corresponding runtime and memory footprint values for a large set of input sizes. We present results from evaluating multiple state-of-the-art language models on this benchmark, highlighting their strengths and weaknesses in handling complexity requirements. In particular, token-space reasoning models are unrivaled in code generation but not in complexity understanding, hinting that they may not generalize well to tasks for which no reward was given at training time.

Primary Area: datasets and benchmarks

Submission Number: 20453