Read news on AI benchmarks with our app.
Read more in the app
Google unveils Gemini 3 claiming the lead in math, science, multimodal, and agentic AI benchmarks
AI benchmarks are a bad joke – and LLM makers are the ones laughing
OpenAI launches program to design new ‘domain-specific’ AI benchmarks
Meta got caught gaming AI benchmarks
This Week in AI: Maybe we should ignore AI benchmarks for now
Anthropic Looks To Fund a New, More Comprehensive Generation of AI Benchmarks
Anthropic looks to fund a new, more comprehensive generation of AI benchmarks
Why most AI benchmarks tell us so little
MLCommons wants to create AI benchmarks for laptops, desktops and workstations
