0

Multimodal RewardBench 2: Evaluating Omni Reward Models for Interleaved Text and Image

Multimodal RewardBench 2 (MMRB2) is a benchmark for reward models on multimodal understanding and generation tasks, featuring expert-annotated preferences and state-of-the-art model evaluations.

Year
2025
Venue
arXiv 2025
Authors
6
Hosting
Abstract onlyARXIV-DEFAULT

Cite

Notes

Only stored in your browser.

Attribution

Abstract & full text
arxiv.org/abs/2512.16899ARXIV-DEFAULT
TL;DR
Semantic Scholar
Attribution policy →

Abstract

Reward models (RMs) are essential for training large language models (LLMs), but remain underexplored for omni models that handle interleaved image and text sequences. We introduce Multimodal RewardBench 2 (MMRB2), the first comprehensive benchmark for reward models on multimodal understanding and (interleaved) generation. MMRB2 spans four tasks: text-to-image, image editing, interleaved generation, and multimodal reasoning ("thinking-with-images"), providing 1,000 expert-annotated preference pairs per task from 23 models and agents across 21 source tasks. MMRB2 is designed with: (1) practical but challenging prompts; (2) responses from state-of-the-art models and agents; and (3) preference pairs with strong human-expert consensus, curated via an ensemble filtering strategy. Using MMRB2, we study existing judges for each subtask, including multimodal LLM-as-a-judge and models trained with human preferences. The latest Gemini 3 Pro attains 75-80% accuracy. GPT-5 and Gemini 2.5 Pro reach 66-75% accuracy, compared to >90% for humans, yet surpass the widely used GPT-4o (59%). The best performing open-source model Qwen3-VL-32B achieves similar accuracies as Gemini 2.5 Flash (64%). We also show that MMRB2 performance strongly correlates with downstream task success using Best-of-N sampling and conduct an in-depth analysis that shows key areas to improve the reward models going forward.

Authors

6