MMMG: a Comprehensive and Reliable Evaluation Suite for Multitask Multimodal Generation

TL;DR

MMMG is a comprehensive benchmark for evaluating multimodal generation models, aligning closely with human judgment and covering diverse tasks and modalities to identify strengths and gaps in current models.

Contribution

The paper introduces MMMG, a new benchmark with 49 tasks across four modalities, designed for reliable automatic and human-aligned evaluation of multimodal generation models.

Findings

MMMG achieves 94.3% agreement with human evaluation.

GPT Image reaches 78.3% accuracy in image generation.

Significant challenges remain in multimodal reasoning and audio generation.

Abstract

Automatically evaluating multimodal generation presents a significant challenge, as automated metrics often struggle to align reliably with human evaluation, especially for complex tasks that involve multiple modalities. To address this, we present MMMG, a comprehensive and human-aligned benchmark for multimodal generation across 4 modality combinations (image, audio, interleaved text and image, interleaved text and audio), with a focus on tasks that present significant challenges for generation models, while still enabling reliable automatic evaluation through a combination of models and programs. MMMG encompasses 49 tasks (including 29 newly developed ones), each with a carefully designed evaluation pipeline, and 937 instructions to systematically assess reasoning, controllability, and other key capabilities of multimodal generation models. Extensive validation demonstrates that MMMG is highly aligned with human evaluation, achieving an average agreement of 94.3%. Benchmarking results on 24 multimodal generation models reveal that even though the state-of-the-art model, GPT Image, achieves 78.3% accuracy for image generation, it falls short on multimodal reasoning and interleaved generation. Furthermore, results suggest considerable headroom for improvement in audio generation, highlighting an important direction for future research.