VisIT-Bench: A Dynamic Benchmark for Evaluating Instruction-Following Vision-and-Language Models

Published: 26 Sept 2023, Last Modified: 02 Nov 2023NeurIPS 2023 Datasets and Benchmarks PosterEveryoneRevisionsBibTeX
Keywords: Vision-language models, Instruction-following, Benchmark, Multimodal chatbots, ELO rating system, Automatic evaluation metric, Dataset collection
TL;DR: Introducing VisIT-Bench, a dynamic benchmark and evaluation metric for vision-language models. It provides rankings, diverse tasks, and enhances model evaluations. VisIT-Bench highlights performance gaps and supports future research.
Abstract: We introduce VisIT-Bench (Visual InsTruction Benchmark), a benchmark for evaluating instruction-following vision-language models for real-world use. Our starting point is curating 70 "instruction families" that we envision instruction tuned vision-language models should be able to address. Extending beyond evaluations like VQAv2 and COCO, tasks range from basic recognition to game playing and creative generation. Following curation, our dataset comprises 592 test queries, each with a human-authored instruction-conditioned caption. These descriptions surface instruction-specific factors, e.g., for an instruction asking about the accessibility of a storefront for wheelchair users, the instruction-conditioned caption describes ramps/potential obstacles. These descriptions enable 1) collecting human-verified reference outputs for each instance; and 2) automatic evaluation of candidate multimodal generations using a text-only LLM, aligning with human judgment. We quantify quality gaps between models and references using both human and automatic evaluations; e.g., the top-performing instruction-following model wins against the GPT-4 reference in just 27% of the comparison. VisIT-Bench is dynamic to participate, practitioners simply submit their model's response on the project website; Data, code and leaderboard is available at
Supplementary Material: pdf
Submission Number: 611