Interactive Benchmarks
This work addresses the problem of unreliable standard benchmarks for the AI research community by proposing a new evaluation paradigm.
This paper proposes Interactive Benchmarks, a new evaluation paradigm that assesses a model's ability to acquire information actively and reason under budget constraints. The framework is instantiated in Interactive Proofs (logic/math) and Interactive Games (strategic reasoning), revealing significant room for improvement in current models in interactive scenarios.
Standard benchmarks have become increasingly unreliable due to saturation, subjectivity, and poor generalization. We argue that evaluating model's ability to acquire information actively is important to assess model's intelligence. We propose Interactive Benchmarks, a unified evaluation paradigm that assesses model's reasoning ability in an interactive process under budget constraints. We instantiate this framework across two settings: Interactive Proofs, where models interact with a judge to deduce objective truths or answers in logic and mathematics; and Interactive Games, where models reason strategically to maximize long-horizon utilities. Our results show that interactive benchmarks provide a robust and faithful assessment of model intelligence, revealing that there is still substantial room to improve in interactive scenarios. Project page: https://github.com/interactivebench/interactivebench