Agents on Rails: lemans goes open source

Another week, another step for Agents on Rails . This one is a big one: lemans , the harness behind every number we’ve published, is now open source. We also ran four new models: Sonnet 5 , Terra , an open-weight Qwen you can run on your own machine, and one that won’t tell us its name. If you’re here for the ride, read on for the tour of lemans. If you’re here for the scores, they’re on the leaderboard , and the raw runs are updated too. Four new models, and one of them has no name Qwen 3.8-...