Alibaba-NLP releases Core-Reranker-8B, a compositional multimodal reranker on Hugging Face

Alibaba-NLP has published Core-Reranker-8B on Hugging Face, an 8B-parameter multimodal reranker fine-tuned from Qwen3-VL-Reranker to better distinguish attribute-object bindings in text and image relevance scoring.

On compositional reasoning benchmarks COLA, SugarCrepe++, and NegBench, it reports an 82.7% total average, 10.7 points above Jina-Reranker.

The model is part of the Core-Embed family, which also includes 2B and 8B embedding models, with Core-Embed-8B reporting a 0.666 total average.