UNICBench: UNIfied Counting Benchmark for MLLM
This provides a rigorous evaluation tool for counting capabilities in MLLMs, addressing a core but previously unstandardized problem for AI researchers.
The authors tackled the lack of a unified counting dataset for multimodal large language models (MLLMs) by creating UNICBench, a benchmark with 5,300 images, 872 documents, and 2,069 audio clips, and found that while MLLMs perform well on basic counting tasks, they show significant gaps on reasoning and hardest partitions.
Counting is a core capability for multimodal large language models (MLLMs), yet there is no unified counting dataset to rigorously evaluate this ability across image, text, and audio. We present UNICBench, a unified multimodal, multi level counting benchmark and evaluation toolkit with accurate ground truth, deterministic numeric parsing, and stratified reporting. The corpus comprises 5,300 images (5,508 QA), 872 documents (5,888 QA), and 2,069 audio clips (2,905 QA), annotated with a three level capability taxonomy and difficulty tags. Under a standardized protocol with fixed splits/prompts/seeds and modality specific matching rules, we evaluate 45 state-of-the-art MLLMs across modalities. Results show strong performance on some basic counting tasks but significant gaps on reasoning and the hardest partitions, highlighting long-tail errors and substantial headroom for improving general counting. UNICBench offers a rigorous and comparable basis for measurement and a public toolkit to accelerate progress.