IPO Finance Agent: Evaluation of LLM Financial Analysts beyond Finance Agent v2, with Automated Rubric Generation -- the Case of the SpaceX (SPCX) IPO

The article introduces the IPO Finance Agent, an extension of the Finance Agent v2 framework, designed to evaluate financial models on IPO due diligence tasks, specifically targeting SEC S-1 filings. This new framework incorporates contextual retrieval to handle the complexity and length of IPO documents, while also featuring an automated rubric generation pipeline for evaluation. The results indicate that Alibaba Qwen 3.7 Max achieves 79.4% accuracy at $0.30 per query, outperforming existing benchmarks, which is significant for practitioners seeking efficient and accurate tools for financial analysis in the IPO domain.