Benchmark RadarAI BENCHMARK PROFILE
FinReportBench
FinReportBench evaluates institution-grade financial report generation using 244 bilingual tasks sourced from 10,000 financial research records. It uses a 35-item rubric covering deliverability, report identity, and institutional completeness, with three judge families.
- Released
- 2026-08-05
- Readiness
- Runnable
- Primary field
- Finance & Economics
Why it matters
It fills the gap in evaluating long-form financial reports for institutional delivery, providing a reliable rubric and public artifacts to measure and improve report generation.
Motivation
Large language models can produce fluent financial analysis, but fluency alone does not establish whether a report is suitable for institutional delivery.
Primary resources
Benchmark Radar records only publicly supported details and links back to primary sources for verification.