Benchmark RadarAI BENCHMARK PROFILE
FinRCA-Bench
FinRCA-Bench is a synthetic benchmark for financial reconciliation root-cause analysis, with 2,250 cases across 14 tables and 15 failure categories, providing evidence retrieval and reasoning evaluation.
- Released
- 2026-08-19
- Readiness
- Runnable
- Primary field
- Finance & Economics
Why it matters
Financial AI systems need reliable evidence retrieval and reasoning, and existing benchmarks conflate the two. FinRCA-Bench separates retrieval evaluation from answer correctness.
Motivation
Large language models are increasingly used to support financial operations, but their apparent reasoning performance can depend on whether they receive the right evidence.
Primary resources
Benchmark Radar records only publicly supported details and links back to primary sources for verification.