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

> A group calling itself the AllSpark team has released Iris-mini and Iris-pro, a pair of open-source search agents that, according to their paper, top the benchmarks among open-weight models in their respective size classes. Both are built on Alibaba's Qwen models and tuned specifically for the job of searching, reading, and reasoning over information to answer hard questions. Search agents are a distinct breed from chatbots. Rather than answering from memory, they plan a series of lookups, pull in outside sources, and stitch the results into a response, which makes them useful for research-style tasks where freshness and citations matter. The interesting part here is the open-weight angle: teams can download these models, inspect them, and run them privately instead of routing queries through a closed API. That the strongest agents in their class come from a smaller team building on open Qwen foundations is a reminder that the frontier of usable AI is not owned solely by the biggest labs. For developers and researchers, it lowers the cost of experimenting with agentic search.

_Section: [Daily AI Updates](https://www.wortins.com/daily-ai) · Source: The Decoder · Published Monday, September 14, 2026_

## Wortins' read

A group calling itself the AllSpark team has released Iris-mini and Iris-pro, a pair of open-source search agents that, according to their paper, top the benchmarks among open-weight models in their respective size classes. Both are built on Alibaba's Qwen models and tuned specifically for the job of searching, reading, and reasoning over information to answer hard questions. Search agents are a distinct breed from chatbots. Rather than answering from memory, they plan a series of lookups, pull in outside sources, and stitch the results into a response, which makes them useful for research-style tasks where freshness and citations matter. The interesting part here is the open-weight angle: teams can download these models, inspect them, and run them privately instead of routing queries through a closed API. That the strongest agents in their class come from a smaller team building on open Qwen foundations is a reminder that the frontier of usable AI is not owned solely by the biggest labs. For developers and researchers, it lowers the cost of experimenting with agentic search.

## Source

[Read the full story at The Decoder](https://the-decoder.com/iris-mini-and-iris-pro-are-the-strongest-open-weight-search-agents-in-their-class/)

## Related coverage

- [The detrimental cost of scaling AI too fast](https://www.wortins.com/story/the-detrimental-cost-of-scaling-ai-too-fast-aeca9f03) — [The Next Web](https://thenextweb.com/news/detrimental-cost-scaling-too-fast-greg-keith)
- [Chatbots can exploit our most basic human drive for attachment](https://www.wortins.com/story/chatbots-can-exploit-our-most-basic-human-drive-for-attachme-b69df919) — [The Guardian](https://www.theguardian.com/commentisfree/2026/sep/14/how-to-have-healthier-relationship-with-ai-chatbots-human-intimacy)
- [AI Agents Are Thirsty for Power](https://www.wortins.com/story/ai-agents-are-thirsty-for-power-07e24890) — [Wired](https://www.wired.com/story/ai-agents-are-thirsty-for-power/)
- [AI models' written reasoning steps correspond to distinct internal patterns, a new study finds](https://www.wortins.com/story/ai-models-written-reasoning-steps-correspond-to-distinct-int-c41550f0) — [The Decoder](https://the-decoder.com/ai-models-written-reasoning-steps-correspond-to-distinct-internal-patterns-a-new-study-finds/)
- [Feeling sad about AI](https://www.wortins.com/story/feeling-sad-about-ai-61bc65ed) — [Simon Willison](https://simonwillison.net/2026/Sep/11/feeling-sad-about-ai/)
- [Delhi High Court bars misuse of AI deepfakes infringing Rajat Sharma's personality rights](https://www.wortins.com/story/delhi-high-court-bars-misuse-of-ai-deepfakes-infringing-raja-ecc55286) — [Bar and Bench](https://www.barandbench.com/news/delhi-high-court-bars-misuse-of-ai-deepfakes-infringing-rajat-sharmas-personality-rights)

---

_Curated and written by [Wortins](https://www.wortins.com) — The daily AI briefing. Every story links to its original source; the "Wortins read" on each is our own original analysis. [About Wortins & our editorial approach](https://www.wortins.com/about)._