# mR3: Multilingual Rubric-Agnostic Reward Reasoning Models

Source: [mR3: Multilingual Rubric-Agnostic Reward Reasoning Models](<https://www.sota2.com/research/paper/68fa7bc51e209131cea8a58d>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-01-30T05:00:04.719Z

Authors: David Anugraha, Shou-Yi Hung, Zilu Tang, Annie En-Shiun Lee, Derry Tanti Wijaya, Genta Indra Winata

Published: 2025-10-01T17:36:59.000Z

## Abstract

Evaluation using Large Language Model (LLM) judges has been widely adopted in English and shown to be effective for automatic evaluation. However, their performance does not generalize well to non-English settings, and it remains unclear what constitutes effective multilingual training for such judges. In this paper, we introduce mR3, a massively multilingual, rubric-agnostic reward reasoning model trained on 72 languages, achieving the broadest language coverage in reward modeling to date. We present a comprehensive study of data and curriculum selection for training to identify effective strategies and data sources for building high-quality reward models, including support for reasoning in the target language. Our approach attains state-of-the-art performance on multilingual reward model benchmarks, surpassing much larger models (i.e., GPT-OSS-120B) while being up to 9x smaller, and its effectiveness is further confirmed through extensive ablation studies. Finally, we demonstrate the effectiveness of mR3 in off-policy preference optimization and validate the quality of its reasoning traces and rubric-based evaluations through human studies with 20 annotators across 12 languages, where mR3 models' reasoning is preferred, including for extremely low-resource languages that are entirely unseen during training. Our models, data, and code are available as open source at https://github.com/rubricreward/mr3.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Multilingual Reward Modeling on MM-Eval Avg. 18 lang](<https://www.sota2.com/research/sota/multilingual-reward-modeling-on-mm-eval-avg-18-lang.md>): Multilingual Reward Modeling; MM-Eval Avg. 18 lang; Accuracy: 85.29.

- [Reward Modeling on RewardBench English](<https://www.sota2.com/research/sota/reward-modeling-on-rewardbench-english.md>): Reward Modeling; RewardBench English; Accuracy: 90.1.

- [Multilingual Reward Modeling on m-RewardBench Avg. 23 langs](<https://www.sota2.com/research/sota/multilingual-reward-modeling-on-m-rewardbench-avg-23-langs.md>): Multilingual Reward Modeling; m-RewardBench Avg. 23 langs; Accuracy: 88.58.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2510.01146>)

[PDF](<https://arxiv.org/pdf/2510.01146.pdf>)
