Benchmark

OpenAI's o3 AI model scores lower on a benchmark than the company initially implied

OpenAI’s o3 AI model scores lower on a benchmark than the company initially implied

vi.sasori.vi April 21, 2025

A discrepancy between first- and third-party benchmark results for OpenAI’s o3 AI model is...

Beyond ARC-AGI: GAIA and the search for a real intelligence benchmark

Beyond ARC-AGI: GAIA and the search for a real intelligence benchmark

vi.sasori.vi April 14, 2025

Join our daily and weekly newsletters for the latest updates and exclusive content on...

Meta’s vanilla Maverick AI model ranks below rivals on a popular chat benchmark

vi.sasori.vi April 11, 2025

Earlier this week, Meta landed in hot water for using an experimental, unreleased version...

Meta finally starts rolling out default end-to-end encryption for Messenger

Meta exec denies the company artificially boosted Llama 4’s benchmark scores

vi.sasori.vi April 7, 2025

A Meta exec on Monday denied a rumor that the company trained its new...

Pixel art of mario jumping on gaming consoles to get a coin.

People are using Super Mario to benchmark AI now

vi.sasori.vi March 4, 2025

Thought Pokémon was a tough benchmark for AI? One group of researchers argues that...

A new benchmark for AI investment: Swift Ventures unveils system to separate talk from action

A new benchmark for AI investment: Swift Ventures unveils system to separate talk from action

vi.sasori.vi December 10, 2024

Join our daily and weekly newsletters for the latest updates and exclusive content on...

$AI’s math problem: FrontierMath benchmark shows how far technology still has to go$

AI’s math problem: FrontierMath benchmark shows how far technology still has to go

vi.sasori.vi November 12, 2024

Join our daily and weekly newsletters for the latest updates and exclusive content on...

Can AI really compete with human data scientists? OpenAI’s new benchmark puts it to the test

Can AI really compete with human data scientists? OpenAI’s new benchmark puts it to the test

vi.sasori.vi October 11, 2024

Join our daily and weekly newsletters for the latest updates and exclusive content on...

LiveBench is an open LLM benchmark using contamination-free test data

LiveBench is an open LLM benchmark using contamination-free test data

vi.sasori.vi June 13, 2024

It’s time to celebrate the incredible women leading the way in AI! Nominate your...

S&P Global launches groundbreaking AI benchmark for financial industry

S&P Global launches groundbreaking AI benchmark for financial industry

vi.sasori.vi April 5, 2024

Join us in Atlanta on April 10th and explore the landscape of security workforce....