Rahil Verma(@RahilVerma13):At Applied Compute most of our RL and eval pipelines grade with an LLM judge. These produce one result per rubric criterion, typically a paragraph of text accompanying a score. For some complicated tasks, grading can be a slow, pricey part of the loop. We swapped a grader on a code QA benchmark in AC2 for a decision grader: one call, a yes/no probability for every criterion at once. On 100 sample tasks (407 criteria), same answers: → ~32× cheaper → ~8× faster → 94% agreement with the LLM judge And it’s even better than the original judge: When the decision grader was confident, it matched the LLM judge 99% of the time. When it wasn't, the decision grader indicated low confidence (30-70%), pointing to ambiguous rubric items. This allowed us to identify noisy tasks and make the dataset cleaner. A cheap, fast, calibrated grader means you can grade more rollouts, ask more questions per call, and downweight or review the shaky calls instead of training on them.

2026.10.06 15:20

At Applied Compute most of our RL and eval pipelines grade with an LLM judge. These produce one result per rubric criterion, typically a paragraph of text accompanying a score. For some complicated tasks, grading can be a slow, pricey part of the loop. We swapped a grader on a code QA benchmark in AC2 for a decision grader: one call, a yes/no probability for every criterion at once. On 100 sample tasks (407 criteria), same answers: → ~32× cheaper → ~8× faster → 94% agreement with the LLM judge And it’s even better than the original judge: When the decision grader was confident, it matched the LLM judge 99% of the time. When it wasn't, the decision grader indicated low confidence (30-70%), pointing to ambiguous rubric items. This allowed us to identify noisy tasks and make the dataset cleaner. A cheap, fast, calibrated grader means you can grade more rollouts, ask more questions per call, and downweight or review the shaky calls instead of training on them.