# Iris-mini and Iris-pro are the strongest open-weight search agents in their class

> Source: <https://www.machinebrief.com/news/iris-mini-and-iris-pro-are-the-strongest-open-weight-search-p2pc>
> Published: 2026-09-13 12:58:18+00:00

# Iris-mini and Iris-pro are the strongest open-weight search agents in their class

[The Decoder](https://the-decoder.com)

        The AllSpark team has released Iris-mini and Iris-pro, two open-source search agents built on Qwen models that lead benchmarks among open-[weight](/glossary/weight) models in their size classes. According to the paper, the [training](/glossary/training) data and models also improved performance on tasks they were never trained for, including general [tool use](/glossary/tool-use) and office work.

The article [Iris-mini and Iris-pro are the strongest open-weight search agents in their class](https://the-decoder.com/iris-mini-and-iris-pro-are-the-strongest-open-weight-search-agents-in-their-class/) appeared first on [The Decoder](https://the-decoder.com).

Get AI news in your inbox

Daily digest of what matters in AI.

## Key Terms Explained

[Decoder](/glossary/decoder)

The part of a neural network that generates output from an internal representation.

[Tool Use](/glossary/tool-use)

The ability of AI models to interact with external tools and systems — browsing the web, running code, querying APIs, reading files.

[Training](/glossary/training)

The process of teaching an AI model by exposing it to data and adjusting its parameters to minimize errors.

[Weight](/glossary/weight)

A numerical value in a neural network that determines the strength of the connection between neurons.
