PRBench · Finance
Scale AI / Professional work · Answers financial-decision questions to assess judgment, derivation, and risk explanations.
What it measures and how
Fixes either Finance's full 600 tasks or Hard's 300, with common search tools, tiers, and judges. Uses the rubric aggregate without counting both sets or treating professional answers as end-to-end office work.
How this evidence is used
Under review: could add financial judgment. Tasks, tools, exports, and redisplay terms need checking. Source listing only; no automatic collection or scoring.
Evaluation limits & attribution
Model judging does not establish completed financial models or spreadsheets. PRBench Legal, Finance, and MCP Atlas all belong to Scale; extra leaderboards do not increase organization weight.
Data license: Official tasks and code are public; licenses do not automatically cover live results. Stable exports and current-result redisplay terms are unconfirmed.
Results are published by Scale AI. Original scores and the NexGateHub consensus index use different scales and cannot be added directly.