Open Source AI Models Closing Gap with Closed: Llama 4 vs GPT-5 Benchmarks
Claude 4 Opus Benchmarks: Anthropics New Model Tops Every Reasoning Test
Elon Musk's xAI Grok 4 Claims Benchmark Records
Elon Musk's xAI has released Grok 4, claiming record-breaking scores on major AI benchmarks. The model shows particular strength in coding a...
AI Hallucination Rate Drops to 2% in Latest Models
The latest generation of AI language models has achieved hallucination rates below 2% on standardized factuality benchmarks. The improvement...
GPT-5.4 Scores Above Human Baseline on OS Automation Benchmark
OpenAI's GPT-5.4 has become the first AI model to exceed human baseline scores on the OSWorld operating system automation benchmark. The ach...