Launched: S&P AI Benchmarks, a solution that evaluates LLMs for finance and business

Kensho launches S&P AI Benchmarks — a publicly accessible leaderboard that rigorously evaluates leading LLMs on real-world finance and business tasks.

Background on today’s LLMs for finance

A look at S&P AI Benchmarks

  • Quantitative Reasoning: Given a question and lengthy documents, can the model perform complex calculations and correctly reason to produce an accurate answer

  • Quantity Extraction: Given financial reports, can a model extract the pertinent numerical information

  • Domain Knowledge: Answer multi-choice questions that would demonstrate strong, fundamental financial knowledge

For a more detailed and technical look at this project, the research paper can be found here.

Submission process

Previous
Previous

Learnings from the lab: Querying S&P Global’s tabular data using LLMs

Next
Next

Beyond innovation: Leveraging the power of machine learning for business growth