VentureBeat Follow MCP-Universe benchmark shows GPT-5 fails more than half of real-world orchestration tasks A new benchmark from Salesforce research evaluates model and agentic performance on real-life enterprise tasks. https://venturebeat.com/ai/mcp-universe-benchmark-shows-gpt-5-fails-more-than-half-of-real-world-orchestration-tasks/ venturebeat.com AI and ML News on Bluesky @ai-news.at.thenote.app bsky.app
