On 3 June, the leading blockchain and AI organizations, self -layer, cyber, sentient among them announced the establishment of the Caba – Crypto Ai Benchmark Alliance. The aim of this initiative led by the community is to determine transparent standards for AI models and the evaluation of crypto agents.
The members of the Alliance are 14 organizations: Alchemy, Cyber, Eigenlaer, Goldsky, iOSG, Lazai, Magic Newton, Metis, MyShell, Opengrade, Rootdata, Sentient, Surf, Thirdweb.
These companies offer data sets, tools and specialized knowledge to develop a benchmarking framework. Every benchmark, openly published on developer platforms, will consist of defined tasks, reference solutions and assessment scripts.
A benchmark for CAIA – Crypto AI agents – is the first release of the Alliance and is currently available. The benchmark offers accurate answer protocol and token-related questions, mapping multi-step tasks and tools such as Block Explorers and APIs to complete tasks. There are tasks in Caia, related to Tokenomics, on-chain analysis, project research and transaction workflows.
New benchmarks are now underway and the Alliance welcomes new contributors. Developers, researchers and protocols are encouraged to participate by submitting models for evaluation or proposing new benchmarkets.
Image: Caiba
Credit : cryptonews.net
