# Latent.Space benchmarks Naive-N0.5-Flash against DeepSeek and Z models

> Original title: Today, we're launching a new series focused on trying new models and products with unbiased reviews.

- Source: Latent.Space
- Published: 2026-11-10T19:04:32.000Z
- Bad Influence: https://badinfluence.news/items/umc5cbsnftgqai84iff6e1djx
- Original: https://x.com/latentspacepod/status/2120231148731478509

## Summary

Latent.Space launches a series of unbiased reviews of new models and products, starting with Naive AI's Naive-N0.5-Flash. The open-weights model is built for AI coding tasks and tuned for maximum tokens per second. Latent.Space ran it against similar models from DeepSeek and Z to measure its speed.

## Post

Today, we're launching a new series focused on trying new models and products with unbiased reviews. 

We're starting with @naiveailab, which has just launched Naive-N0.5-Flash, a new open-weights model built for AI coding tasks and tuned to generate as many tokens per second as possible. 

The question is: how fast is it, exactly? We ran it through its paces against similar models from DeepSeek and Z. https://latent.space/p/naiveai/