Benchmarks
Breaking New Ground: humanity.ai Sets New Benchmark Records with iCon Modular AI Paid Members Public
humanity.ai's modular AI beats leading models on key benchmarks, delivering superior reasoning with 300B parameters, all running on MacBooks, not datacenters. Hardware-efficient, private, and fully scalable.
ARC-AGI-2: challenge accepted Paid Members Public
Our team has begun preparing our system to excel in ARC-AGI-2, one of the most renowned benchmarks in Artificial General Intelligence. Stay tuned!