Cross-encoders and post-retrieval ranking improvements.
LightOn says its 150M multi-vector retriever is pushing BrowseComp-Plus close to saturation, with results showing search-call behavior and retriever choice matter nearly as much as model size. Retrieval engineers should watch multi-hop setup and tool-calling limits before copying the benchmark.
LightOn’s late-interaction retriever paired with GPT-5 reached 87.59 accuracy on BrowseComp-Plus while using fewer search calls than larger baselines. It suggests deep-research quality may now hinge more on retrieval architecture than on swapping in ever larger LLMs.
Mixedbread introduced Wholembed v3 as a retrieval model for text, image, video, audio, and multilingual search. Benchmark it on fine-grained retrieval tasks if single-vector embeddings have been collapsing in your pipeline.
