PresentBench: A Fine-Grained Rubric-Based Benchmark for Slide Generation

TL;DR

PresentBench introduces a detailed, rubric-based benchmark with 238 instances and 54 checklist items per instance to evaluate automated slide generation, enabling more precise assessment aligned with human preferences.

Contribution

This paper presents PresentBench, a novel fine-grained, rubric-based benchmark for evaluating slide generation, addressing the limitations of coarse-grained assessments and improving evaluation reliability.

Findings

PresentBench provides more reliable evaluation results than existing methods.

It exhibits significantly stronger alignment with human preferences.

NotebookLM outperforms other slide generation methods.

Abstract

Slides serve as a critical medium for conveying information in presentation-oriented scenarios such as academia, education, and business. Despite their importance, creating high-quality slide decks remains time-consuming and cognitively demanding. Recent advances in generative models, such as Nano Banana Pro, have made automated slide generation increasingly feasible. However, existing evaluations of slide generation are often coarse-grained and rely on holistic judgments, making it difficult to accurately assess model capabilities or track meaningful advances in the field. In practice, the lack of fine-grained, verifiable evaluation criteria poses a critical bottleneck for both research and real-world deployment. In this paper, we propose PresentBench, a fine-grained, rubric-based benchmark for evaluating automated real-world slide generation. It contains 238 evaluation instances, each supplemented with background materials required for slide creation. Moreover, we manually design an average of 54.1 checklist items per instance, each formulated as a binary question, to enable fine-grained, instance-specific evaluation of the generated slide decks. Extensive experiments show that PresentBench provides more reliable evaluation results than existing methods, and exhibits significantly stronger alignment with human preferences. Furthermore, our benchmark reveals that NotebookLM significantly outperforms other slide generation methods, highlighting substantial recent progress in this domain.