Vals AI News

Follow us on

X (Twitter)LinkedIn

Featured Articles

How 90 Claude Opus 5.5 agents found a 27-year-old compound in 3 days to solve computing's heat problem

How 90 Claude Opus 5.5 agents found a 27-year-old compound in 3 days to solve computing's heat problem

Economic 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

An Independent Evaluation of TypeSafe's Jev

Claude Opus 5.5 agents find two room-temperature magnetic semiconductor candidates

Vals Web Search Index: evaluating search for real work

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

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