What is the GDPval-MM leaderboard?

The GDPval-MM leaderboard ranks 3 AI models based on their performance on this benchmark. Currently, GPT-5.5 by OpenAI leads with a score of 0.849. The average score across all models is 0.754.

What is the highest GDPval-MM score?

The highest GDPval-MM score is 0.849, achieved by GPT-5.5 from OpenAI.

How many models are evaluated on GDPval-MM?

3 models have been evaluated on the GDPval-MM benchmark, with 0 verified results and 3 self-reported results.

Where can I find the GDPval-MM paper?

The GDPval-MM paper is available at https://arxiv.org/abs/2510.04374. The paper details the methodology, dataset construction, and evaluation criteria.

What categories does GDPval-MM cover?

GDPval-MM is categorized under finance, general, multimodal, and reasoning. The benchmark evaluates multimodal models.

All benchmarks

GDPval-MM

GDPval-MM is the multimodal variant of the GDPval benchmark, evaluating AI model performance on real-world economically valuable tasks that require processing and generating multimodal content including documents, slides, diagrams, spreadsheets, images, and other professional deliverables across diverse industries.

GPT-5.5 from OpenAI currently leads the GDPval-MM leaderboard with a score of 0.849 across 3 evaluated AI models.

Paper