Rio de Janeiro's city government model Rio3.5 beats Qwen3.7 in recent benchmarks
twitter.com
June 14, 2026
1 min read
🔥🔥🔥🔥🔥
54/100
Summary
Alibaba Qwen3.7 slowly fading into irrelevance at the frontier due to proprietary stance. In it's place we have Minimax M3 and... *checks notes* Rio 3.5 397b, made by the municipal IT company of Rio de Janeiro's city government. huggingface.co/prefeitura-rio…
Coverage & discussions
Hacker News · twitter.com
Community discussions
Community Sentiment
Positives
- The funding of a fine-tuned model by a city government highlights innovative applications of AI in public services, potentially setting a precedent for other municipalities.
- The use of the SwiReasoning framework in Qwen demonstrates advancements in model architecture that could enhance reasoning capabilities in AI applications.
Concerns
- Benchmarks in AI are often gamed, making them unreliable indicators of true model performance, which raises concerns about the validity of claims made by smaller teams.
- The practice of 'benchmaxxing' suggests that many in the community are skeptical about the authenticity of performance claims, undermining trust in benchmark results.
