Skip to content

CodeMago

Now

7:32 PMBinance says North Korea used fake job opening and internal AI in record theft 4:32 PMGoogle launches PLE, benchmark with 85 real engineering tasks for AI agents 12:32 PMCZ warns of more AI attacks after US$ 6.3 billion theft from Binance 11:02 AMAnthropic files for IPO and plans to list ANT stock on Nasdaq 8:31 AM42AI emerges from stealth with $62.5M to predict human behavior 6:32 AMApple hits record iPhone sales without launching a new base model 7:32 PMNew York Times sues Brave for scraping paywalled articles to feed AI 7:06 PMAnthropic warns it may be nearing RSI, the AI that improves itself

News

Follow

Benchmarks

AI rankings and tests: LMArena, SWE-bench, ARC-AGI, GPQA and Artificial Analysis. Who moved up, who fell, and by how much.

Google launches PLE, benchmark with 85 real engineering tasks for AI agents

Test with 30 mechanical, 27 electrical, 18 civil and 10 structural tasks measures deliverables, and the best AI scored 48.3% on the hidden set.

OpenAI launches LifeVal test to measure AI on real-life tasks

Announced on November 2, 2026, the benchmark evaluates caregiving, home management and public services by final outcome.

GDPx: new benchmark tests AIs across 11 areas and top score is just 12.0%

SemiAnalysis launched GDPx with 206 real-world tasks; Claude Opus 5.5 leads with 12.0%, ahead of Gemini 4 Carbon and GPT-6 Astra.

Intelligence Index v5 puts Claude Opus 5.5 on top and widens open-weight gap

New methodology uses 60% private tests and leaves Astra at 57 and Sol at 55 points behind the leader, according to Artificial Analysis.