FrontierML tests whether agents turn bigger budgets into better models
FrontierML gives AI agents $10, $50, or $200 per task and tests whether extra spending produces better models, a practical measure of research judgment rather than just reasoning. Agents choose the architecture, data, GPUs, training runs, and experiments, then submit an inference server for held-out tests on an air-gapped H100. The benchmark has 21 long-horizon tasks, and the authors report that stronger agents reliably improve when given more capital.