Nvidia-backed Reflection AI unveils Beam, its first open-weight model, which it says rivals GLM-5.2 on reasoning with far ...

AI benchmark flaws impact market confidence in Anthropic. Anthropic's best AI model by October 2026 now at 35.5% YES.

Anthropic has introduced Claude Haiku 5.5 AI model. The company says the new model is its "cheapest, fastest, and most ...

AI benchmarks are useful in assessing AI model performance. But when most developers report high scores, benchmarks become less meaningful. A recent study found that some large AI ...

Google Gemini 4 Argon tops the Arena AI benchmarks with a 1 million token output limit. Read how it outperforms Claude Opus 5 ...

Google has unveiled Gemini 4 Argon, a new frontier model focused on coding, enterprise work, and cybersecurity, with access ...

Before a new AI model reaches the public, its developers run it through a battery of tests known as "benchmarks," which score ...

Are AI benchmarks really the gold standard we’ve been led to believe? Matt Wolfe walks through how these widely accepted metrics, designed to measure the performance of artificial intelligence ...

Dubai-based Anticloud reports results from a benchmark in which its 27B-parameter PAX v52 model generated structured research frameworks for 20 open problems across multiple scientific fields.Dubai, ...

We know models cheat. A new benchmark measures how much, and on what tasks.

Argo-Bench found the top AI model fully solved just 34.8% of enterprise data tasks, exposing gaps in AI agent reliability and ...