Skip to main content

TencentSpecialist modelWeights available

Yuanbao-Reranker-4B

PopularityRank 13 of 19 specialist models

21out of 100first value

usage data only, range 7 to 35

Summary

Yuanbao-Reranker-4B is a text model for ordering search results. It scores documents for their relevance to a query.

The middle member of the family builds on Qwen3-4B. Its model card lists a context of up to 8,192 tokens, and its weights are available under Apache 2.0.

Popularity compared

How often the model is searched for, used and mentioned, compared with every model of its category.

Popularity index

0 to 100, higher is more popular

20 of 21 models

As of November 2026 · Source: gradually.ai popularity index

Over time

First value from November 20, 2026. The timeline appears from the second week.

What is gaining popularity right now, across models, vendors, harnesses and AI subscriptions, is collected in All AI trends.

All specifications

Architecture

Checkpoint
Yuanbao-Search/Yuanbao-Reranker-4B
Source: Checkpoint
Model class
Text reranker for scoring the relevance of search results.
Source: Model class
Base model
Qwen3-4B
Source: Base model

Input and output

Input
Task instruction, search query, and a text document.
Source: Input
Output
A relevance score between 0 and 1 based on yes and no probabilities.
Source: Output
Context window
Up to 8,192 tokens.
Source: Context window

Watermarking and provenance

AI watermarking refers to invisible signals embedded in the output. Visible marks and provenance metadata are listed separately. Unknown means there is insufficient evidence for that particular field.

AI watermarking
Unknown
no source
Watermarking technique
Not known
no source

Licence and access

Weights license
Apache License 2.0
Source: Weights license
Shutdown
None announced
no source

Further details

Research paper
The authors submitted their paper on November 7, 2026. It does not give a separate release date for the weights.
Source: Research paper