Vals AI News

Follow us on

X (Twitter)LinkedIn

Featured Articles

Google Releases a New Flagship A.I. Model, With Limits

Google Releases a New Flagship A.I. Model, With Limits

New York Times

Can Independent Testing Make AI Safer?

Can Independent Testing Make AI Safer?

Bloomberg

Vals AI Launches Excel Modeling Benchmark For Finance Agents

Vals AI Launches Excel Modeling Benchmark For Finance Agents

Let's Data Science

All Articles

Google's Gemini 4 Argon evaluated across our benchmark suite

Has the Bitter Lesson Come for AI Detectors?

AI's mental health test

Anthropic's Claude Sonnet 5.5 evaluated across our benchmark suite

Ten Claude Sonnet 5.5 agents prove the Thomson problem at N = 7 in Lean

Chatbots are still falling short in mental health conversations with kids

Washington Post

Anthropic's Claude Opus 5.5 evaluated across our benchmark suite

OpenAI's GPT-6 Luna evaluated across our benchmark suite

OpenAI's GPT-6 Sol evaluated across our benchmark suite

Ten Claude Opus 5.5 agents prove a faster shortest-path algorithm in Lean