Vals AI News

Follow us on

X (Twitter)LinkedIn

Download Press Kit

Featured Articles

A.I. Agents: They’re Fun. They’re Useful. But Don’t Give Them the Credit Card.

A.I. Agents: They’re Fun. They’re Useful. But Don’t Give Them the Credit Card.

New York Times

Meta Announces New AI Model in Major Test of Company's Ambitions

Meta Announces New AI Model in Major Test of Company's Ambitions

Wall Street Journal

The Winners (and Losers) of This New Vibe-Coding Benchmark Will Surprise You

The Winners (and Losers) of This New Vibe-Coding Benchmark Will Surprise You

Inc

All Articles

Qwen 3.6 Plus evaluated!

Gemma 4 31B IT is a size-efficient open release

Meta Muse Spark ranks 3 on the Vals Index

GLM 5.1 takes the top open-weight spot on the Vals Index

Trinity Large Thinking on Vals Index

SWE-bench Harness Update

GPT 5.4 Mini Evaluated!

GPT 5.4 Nano evaluated on our full benchmark suite

MiniMax M2.7 Evaluated!

Grok 4.20 Beta (03/09) evaluated on our full benchmark suite