Qwen-AgentWorld 35B A3B
Shares rank 33 of 39 open-weight language models by recommenders
Qwen's post-trained 35B A3B agent model that people find stronger than Qwen 3.6 for agentic work and developer help. Critics note reasoning loops and questionable world-model branding.
Qwen's post-trained 35B A3B agent model that people find stronger than Qwen 3.6 for agentic work and developer help. Critics note reasoning loops and questionable world-model branding.
12 people gave an opinion
- recommend it
- 8
- criticize it
- 4
- approval share
- 67%
Recommended in 3 of 13 months
- November 2025: not recommended
- December 2025: not recommended
- January 2026: not recommended
- February 2026: not recommended
- March 2026: not recommended
- April 2026: not recommended
- May 2026: not recommended
- June 2026: recommended
- July 2026: recommended
- August 2026: recommended
- September 2026: not recommended
- October 2026: not recommended
- November 2026: not recommended (month in progress)
Why it doesn’t carry the badge
- 8 people recommend itNeeds 10 or more, not met.
- 2 recommenders for every criticNeeds 2 to 1 or better, met.
- Recommended in 3 of 13 monthsNeeds 4 or more, not met.
The same three rules apply to every product, and the badge can’t be bought. How the badge works
What people say about it
The reasons people give, with the number of comments that give each one. Open a reason to read what they said.
Why people recommend it
Each mark is one comment
Strong agentic and workflow-state performance
“This might be pretty big. One of my biggest frustrations with smaller models is their failure to track workflow state at a high level.”
Comment from 24 Jun 2026 in “Qwen-AgentWorld: Language World Models for General Agents” “AgentWorld is _fantastic_. i just migrated "down" from the 122B A10B qwen model to agentworld”
Comment from 29 Jun 2026 in “Qwen 3.6 27B is the sweet spot for local development” “definitely better than 3.6 35B A3B on all dimensions, but especially for agentic use”
Comment from 14 Aug 2026 in “Qwen3.8-27B”
What people warn about
Each mark is one comment
Overstated world model branding
“qwen has decided to rebrand certain LLMs that were trained slightly differently as "world models"”
Comment from 24 Jun 2026 in “Qwen-AgentWorld: Language World Models for General Agents” “probably more of a data scale win than a world model breakthrough”
Comment from 24 Jun 2026 in “Qwen-AgentWorld: Language World Models for General Agents”
Other open-weight language models people recommend
The four most recommended other open-weight language models, with the same counts for each, so you can compare like for like. The tick on each bar marks the 2 to 1 line the badge needs.
| Product | Recommend | Criticize | Approval | Months | Owned | Badge |
|---|---|---|---|---|---|---|
| Qwen 3.8 27B | 1,173 | 426 | 73% | 13 | 2 mo32 owners | Approved |
| Z.ai GLM | 1,043 | 384 | 73% | 13 | 2 mo52 owners | Approved |
| Kimi | 931 | 359 | 72% | 13 | 1 mo26 owners | Approved |
| Gemma 4 | 713 | 249 | 74% | 13 | 1 mo14 owners | Approved |
| Qwen-AgentWorld 35B A3BThis page | 8 | 4 | 67% | 3 | — | — |
What people said
14 of the 15 comments that mention it, newest first. Each links to the original comment.
“definitely better than 3.6 35B A3B on all dimensions, but especially for agentic use”
“They did release AgentWorld recently, a post-train of the 3.6 MoE, so they're still doing some open things”
“Both of them are good developer partners for an engineer who wants more of a second pair of eyes and a rubber duck”
“performs worse than Qwen 3.6 and Qwen AgentWorld on my benchmarks”
“AgentWorld is _fantastic_. i just migrated "down" from the 122B A10B qwen model to agentworld”
“Qwen's new AgentWorld model is good too”
“seems like it could handle the job now with good prompting”
“these work but seem to loop in reasoning a lot”
“seems like it is either broken or it does not work on dockerized llama.cpp”
“qwen has decided to rebrand certain LLMs that were trained slightly differently as "world models"”
“can run locally on a gaming card with quant”
“probably more of a data scale win than a world model breakthrough”
“This might be pretty big. One of my biggest frustrations with smaller models is their failure to track workflow state at a high level.”
“The labels of the very first chart (figure 1, bottom left) are obviously wrong”
Counts come from 1,795,640 Hacker News comments, November 2025 to November 2026. How we count. Report a mistake.