Photo: Pachon in Motion / Pexels
The crypto-native lab wants to bring SWE-bench-style rigor to evaluating algorithmic trading agents in perpetual futures markets
Dolores Research just dropped an open-source framework designed to do for AI trading agents what SWE-bench did for coding agents: give everyone a standardized, reproducible way to measure whether these things actually work.
The project, called WAGMI Bench, evaluates AI trading agents across 13 historical periods in the BTC perpetuals market, covering everything from the COVID crash to the window around ETH approvals. Each agent faces 3,150 decision points under consistent rules. No cherry-picking favorable time windows, no conveniently omitting the drawdowns.
What WAGMI Bench actually measures #
The benchmark’s core philosophy is a deliberate departure from the standard crypto trading flex. Instead of leading with profit-and-loss numbers, WAGMI Bench evaluates agents on survival and engagement metrics.
The initial results from the Classic 13 study (v1) tested five models plus one mechanical baseline. Dolores Research hasn’t positioned any single model as a winner. The emphasis is on the framework itself, not on crowning a champion. The project is released under an Apache-2.0 license, meaning anyone can fork it, extend it, or run their own agents through the gauntlet.
The inspiration from SWE-bench is explicit. SWE-bench became the de facto standard for measuring whether AI coding agents could actually resolve real software engineering tasks. WAGMI Bench is attempting the same intervention for trading agents.
The token layer and Virtuals Protocol #
Alongside the benchmark, Dolores Research launched a community token called $DOLORES through the Virtuals Protocol on Robinhood Chain. The token allocated 2% of its total supply to veVIRTUAL stakers, tying the project into the broader Virtuals ecosystem.
Dolores Research has framed the token as a coordination and research support layer rather than a governance mechanism. The token doesn’t influence benchmark results or agent performance metrics.
The launch timing places $DOLORES within a broader promotional wave around the Virtuals Protocol in late August 2026.
Why the timing matters #
WAGMI Bench arrives at a moment when the infrastructure for agent-based trading is maturing rapidly. The CFTC approved a true BTC perpetual in May 2026, a regulatory milestone that brought US-regulated perpetual futures closer to the products that have dominated offshore exchanges for years.
Major exchanges have also been building out tools and APIs specifically designed for AI agents. Coinbase and Binance have both invested in infrastructure that makes it easier for automated systems to interact with their platforms.
For developers building trading agents, the practical implication is straightforward: there’s now a common playing field. Instead of each team defining its own success criteria, WAGMI Bench offers a shared set of conditions that make apples-to-apples comparisons possible. Disclosure: This article was edited by Editorial Team. For more information on how we create and review content, see our