FinanceBench B

AI benchmark · Multi-Domain

Domains
Multi-Domain Coding
Tier
B why
Snapshot

Open benchmark ↗arxiv.org/abs/2311.11944

What is FinanceBench?

FinanceBench measures how well LLMs answer open-book financial questions about publicly traded companies using source documents and evidence.

  • Finance mostly

    “FinanceBench is a first-of-its-kind test suite for evaluating the performance of LLMs on open book financial question answering (QA).”
    arxiv.org/abs/2311.11944 ↗

Paper: arxiv.org/abs/2311.11944 ↗

Lineage

Benchmarks this one is built on and built from: versions, subsets, extensions and the indexes that combine them.

Derived benchmarks

Tier B

B

Established: 15 or more models scored, or curated RL directories rate it.

How much stands behind a tier: usage, who backs it, a confirmed line from its own site or paper, and a clear read on X. High with three of the four, medium with two, low otherwise.

  • 5 models scored
  • listed with Patronus AI
  • in curated RL directories (4 pts)

On X · mixed, low buzz, from 5 posts about FinanceBench in the last month

FinanceBench appears mainly as a cited score in PageIndex promotion, with one post noting its 98.7% adjudicated versus 90.7% strict results differ.

@ReignSwords ↗ · @ReignSwords ↗ · @pkdige ↗

How we got to tier B
  1. Adoption: 5 models scored; listed with Patronus AI. Tier C.
  2. On X: mixed, low buzz. “FinanceBench appears mainly as a cited score in PageIndex promotion, with one post noting its 98.7% adjudicated versus 90.7% strict results differ.” No move.
  3. In curated RL directories: 4 points, a floor of B. Raised to B.
  4. Confirmed: a line from its own site or paper places it.

A clear view on X moves a tier one step up or down; most entries don't move. How tiers work.

Where FinanceBench sits

Its domain on the map, live. Hover a logo for its name; click to open it. Open it on the full map

The galaxy could not load. See every vendor on the board.

More Multi-Domain AI benchmarks

Multi-Domain RL environments

Next: browse all benchmarks. Entry from the RL Research daily scrape of public sources, 2026-11-05 snapshot.