# grand-exchange — see environments/grand_exchange for what it measures. # # uv run eval @ configs/grand_exchange.toml --model num_tasks = 16 num_rollouts = 2 [env.taskset] id = "grand-exchange" num_items = 5 # items in the basket, one per price tier visible = 56 # ticks the model reads held_out = 30 # ticks its orders are executed against [env.agent.harness] id = "null" # pure-trace reward: one completion, no tools, no runtime