Meta got caught gaming AI benchmarks
Meta recently released two new Llama 4 models, Scout and Maverick, with Maverick claiming to outperform competitors on LMArena but ...
Tuesday, July 29, 2025
Tag: benchmarks
Meta’s benchmarks for its new AI models are a bit misleading
Meta recently released the AI model Maverick, which ranks second on LM Arena, a test where human raters compare outputs ...
Asia-Pacific stocks rise after soft U.S. inflation report pushes two Wall Street benchmarks up
Asia-Pacific markets rose on Thursday following a soft U.S. inflation report, with Australia's S&P/ASX 200 up 0.32%, Japan's Nikkei 225 ...
Check your expectations — Nvidia’s RTX 50-series benchmarks don’t tell the full story
Nvidia unveiled its RTX 50-series GPUs at CES 2025, claiming they are twice as fast as the previous generation thanks ...
OpenAI's o3 performance on benchmarks suggests that test-time compute is the next best way to scale AI models, raising new questions about costs and usage (Maxwell Zeff/TechCrunch)
Maxwell Zeff of TechCrunch reports that OpenAI's o3 performance on benchmarks indicates that test-time compute is becoming a key factor ...
Anthropic looks to fund a new, more comprehensive generation of AI benchmarks
Anthropic, a leading AI research company, is seeking funding to develop a new set of benchmarks for evaluating artificial intelligence ...
Latest Pixel 9 leak gives us a look at the Tensor G4 specs and benchmarks
Exciting news for tech enthusiasts as the latest Pixel 9 leak reveals details about the upcoming Tensor G4 processor's specs ...
News Summarized. Time Saved. Bite-sized news briefs for busy people. No fluff, just facts.