AIThe New Stackabout 13 hours ago
Claude Leads New Agent-Building Benchmark
9 min read
Anthropic's Claude model achieved the highest score on Hyper-τ-bench, a new benchmark testing an AI agent's ability to build another agent from scratch. The top-performing model still passed fewer than 25% of the tests, highlighting the current difficulty of fully autonomous agent creation.
Level
Hype check
Tap to vote and see what everyone thinks.
In this storyAnthropic
Summary by ByteBrief
