Google DeepMind Seals Gemini Test to Protect AI Benchmarks

Google DeepMind tested Gemini 2.5 Flash Lite behind a cryptographic wall designed to protect confidential AI benchmarks and ...
ZDNet

Benchmark test of AI's performance, MLPerf, continues to gain adherents

Wednesday, the MLCommons, the industry consortium that oversees a popular test of machine learning performance, MLPerf, released its latest benchmark test report, showing new adherents including ...
ZDNet

In latest benchmark test of AI, it's mostly Nvidia competing against Nvidia

Although chip giant Nvidia tends to cast a long shadow over the world of artificial intelligence, its ability to simply drive competition out of the market may be increasing, if the latest benchmark ...
Chemistry World

Benchmark flaws may be distorting AI drug-discovery leaderboards

Audit identifies subtle but consequential issues, such as conflicting labels and train-test leakage, in numerous benchmark ...
VentureBeat

LiveBench is an open LLM benchmark that uses contamination-free test data and objective scoring

Want smarter insights in your inbox? Sign up for our weekly newsletters to get only what matters to enterprise AI, data, and security leaders. Subscribe Now A team of Abacus.AI, New York University, ...