According to Chainwire, Wallet V launched a public performance benchmark on June 15 for AI trading agents configured by its users on decentralized derivatives platforms Hyperliquid and Aster. The benchmark aggregates performance data from 688 agents created over the prior two months, each using a large language model selected by users to generate trading decisions.
Across the cohort of seven large language model families, 42 percent of agents recorded a profit and loss balance of zero or higher. Peak agent-level return on investment ranged from negative 30 percent on the lowest-performing model to positive 307 percent on the highest. Agents executed perpetual futures strategies across four asset classes including major digital assets such as BTC, ETH, and SOL; equities; commodities including gold, silver, and oil; and major foreign exchange pairs.