Papers/2608.26317
🧪 Test?View on arXiv

Modality Maturity Index: A benchmark for assessing multimodal capabilities of omni models

Not provided in the content

multimodalevaluationbenchmarkinglanguage models
2608.26317
Builder Relevance
70%
1h ago

Abstract

The paper proposes the Modality Maturity Index (MMI), a benchmark for evaluating multimodal capabilities of large language models across five modalities and their combinations.

Reality Card

Core Claim

The introduction of the Modality Maturity Index (MMI) provides a comprehensive framework for assessing the multimodal capabilities of large language models, revealing low modality presence scores across frontier models.

Method / Result

The Modality Presence Score (MPS) for five frontier multimodal models ranges from 15.6 to 34.9.

Limitations

The low availability of returned modalities limits the ability to grade and assess model performance accurately.

Paper to code

Verified implementation resources so builders can test the paper’s claims instead of stopping at the abstract.

No verified implementation link has been attached yet. AIBuzzHub will keep this panel separate from unverified search results.
← Back to all papers