16x EvalBlog
Read the latest blog posts from 16x Eval.
New Claude Models Default to Full Code Output, Stronger Prompt Required
June 18, 2025
The latest Claude models are more likely to output full code, even if you ask for only the changes. We examine this behavior, how it compares to older models and competitors, and how to get concise output.
Why Gemini 2.5 Pro Won't Stop Talking (And How to Fix It)
June 1, 2025
Learn how to manage Gemini 2.5 Pro's verbose output, especially for coding, and compare its behavior with other models like Claude and GPT.
Claude Opus 4 and Claude Sonnet 4 Evaluation Results
May 25, 2025
A detailed analysis of Claude Opus 4 and Claude Sonnet 4 performance on coding and writing tasks, with comparisons to GPT-4.1, DeepSeek V3, and other leading models.
Mistral Medium 3 Coding and Writing Evaluation
May 9, 2025
A detailed look at Mistral Medium 3's performance on coding and writing tasks, compared to top models like GPT-4.1, Claude 3.7 Sonnet, and Gemini 2.5 Pro.