Phoenix-VL 1.5 Medium Technical Report

TL;DR

Phoenix-VL 1.5 Medium is a large, multimodal, multilingual foundation model tailored for Singapore, demonstrating strong performance on local benchmarks and maintaining broad-spectrum intelligence.

Contribution

It introduces a regionally adapted, multimodal, multilingual foundation model with novel training and evaluation methods for localized knowledge and safety.

Findings

Achieves state-of-the-art results on Singapore-specific benchmarks.

Maintains competitive performance on global multimodal and multilingual tasks.

Introduces a new evaluation suite for localized knowledge and safety.

Abstract

We introduce Phoenix-VL 1.5 Medium, a 123B-parameter natively multimodal and multilingual foundation model, adapted to regional languages and the Singapore context. Developed as a sovereign AI asset, it demonstrates that deep domain adaptation can be achieved with minimal degradation to broad-spectrum intelligence and alignment. Continued pretraining was performed on Mistral Medium 3.1 using a localized 1-trillion tokens multimodal corpus, followed by a 250-billion tokens long-context extension phase. Subsequent post-training incorporated a novel human-annotated Singapore multimodal dataset and curated textual corpus on Singapore culture, knowledge, and legislation, totaling 22-billion tokens. An additional 5 billion tokens of model alignment was performed through Online Direct Preference Optimization. Phoenix-VL 1.5 Medium achieves state-of-the-art performance for its size on Singapore multimodal, legal, and government policy benchmarks while remaining globally competitive on general multimodal intelligence, multilingual, and STEM benchmarks. We also introduce a novel evaluation suite encompassing localized knowledge benchmarks and an institutionally aligned model behavior and safety framework. We report the data curation principles, training methodology, and highlight benchmark and inference performance.