Domain on the map
RL environments and benchmarks for finance
Financial analysis and operations, such as building models, reading filings and working with market and accounting data.
- RL environments
- 8
- AI benchmarks
- 61
- Shares entries with
- 16 categories
Snapshot 2026-11-05. How categories are built · Where the data comes from
In short
- What are RL environments for finance?
- A simulated workplace where an AI agent practises a task (a code repository, a browser, business software) and an automatic grader scores each attempt. Labs train on thousands of these attempts. Bought to improve models. For finance, that means financial analysis and operations, such as building models, reading filings and working with market and accounting data.
- Who builds RL environments for finance?
- Surge AI, Halluminate, General Reasoning, Aptura, Third Moment and Rise Data Labs, among 7 confirmed below.
- What are the main finance benchmarks for LLMs?
- Hy-FinmodelBench v2, Real-World Finance v2, WebBench, BacktestBench, BizFinBench and CFLUE, among 57 confirmed below.
RL environments 8
- Surge AI
- Halluminate
-
General Reasoning
Covers finance“Every frontier AI model lost money when tasked with betting on Premier League matches over a full season, a new benchmark reveals.” source ↗
Sells RL environments“An open resource for discovering and experimenting with community RL environments with simple API endpoints and autoscaled infrastructure.” source ↗
- Aptura
-
Third Moment
No line from its own site or paper places it in Finance yet; the catalog lists it here.
-
Rise Data Labs
No line from its own site or paper places it in Finance yet; the catalog lists it here.
- Dissei
1 not yet confirmedListed in the catalog; no line from its own site or paper confirms it yet.
AI benchmarks 61
-
Hy-FinmodelBench v2
Tests finance“Hy-FinmodelBench v2 (internal) | **57.0** | 51.3\* | 52.5\* | 57.8\* | 52.4\* | 65.3\* | 66.0\* |” source ↗
-
Real-World Finance v2
Tests finance“assesses a model’s ability to complete complex, long-horizon financial-analysis tasks of the kind performed by finance professionals” source ↗
-
WebBench
No line from its own site or paper places it in Finance yet; the catalog lists it here.
-
BacktestBench
Tests finance“we introduce BacktestBench, the first large-scale benchmark for automated quantitative backtesting.” source ↗
-
BizFinBench
Tests finance“BizFinBench: A Business-Driven Real-World Financial Benchmark for Evaluating LLMs” source ↗
-
CFLUE
Tests finance“a novel and comprehensive benchmark designed to assess the understanding and processing capabilities of large language models within the context of Chinese financial language.” source ↗
-
Ebisu
Tests finance“We introduce Ebisu, a benchmark for native Japanese financial language understanding” source ↗
-
FCMBench
Tests finance“FCMBench is the first large-scale and privacy-compliant multimodal benchmark for real-world financial credit applications” source ↗
-
Fin-Bias
Tests finance“a benchmark for evaluating LLM investment decision-making when faced with uncertainty and possible human-biased opinions” source ↗
-
FinVerBench
Tests finance“We introduce FinVerBench, a benchmark and validity study for financial statement verification” source ↗
-
ForecastBench-Sim
No line from its own site or paper places it in Finance yet; the catalog lists it here.
-
TaxBench
Tests finance“TaxBench is a technical benchmark for evaluating how well AI models perform on real-world tax tasks — including tax knowledge and judgment, tax calculations, and agentic question answering” source ↗
-
Advancing ESG Intelligence
Tests finance“An Expert-level Agent and Comprehensive Benchmark for Sustainable Finance” source ↗
-
CFMME
Tests finance“we introduce CFMME, a novel Chinese financial multimodal evaluation benchmark.” source ↗
-
EnterpriseArena
Tests finance“We introduce EnterpriseArena, a 132-month CFO simulator that evaluates long-horizon resource allocation under uncertainty in a FinTech lending firm.” source ↗
-
Fin-RATE
Tests finance“we introduce Fin-RATE, a benchmark built on U.S. Securities and Exchange Commission (SEC) filings and mirroring financial analyst workflows” source ↗
-
FinChain
Tests finance“AllFinance SpecificMath EnhancedGeneral Purpose Open” source ↗
-
FinEval
Tests finance“FinEval, a benchmark designed to evaluate LLMs' financial domain knowledge and practical abilities.” source ↗
-
StakeBench
Tests finance“Existing financial NLP benchmarks often rely on labels supplied by outside observers, measuring how language is perceived rather than what speakers have committed to in the market.” source ↗
-
FINESSE-Bench
Tests finance“we present FINESSE-Bench, a suite of eight specialized benchmarks comprising 3,993 questions for hierarchical evaluation of financial competencies in LLMs.” source ↗
-
FrontierFinance
Tests finance“An open benchmark for frontier financial intelligence, measuring how well AI systems support the full investment workflow, from screening to earnings analysis.” source ↗
-
FinQA
Tests finance“we propose a new large-scale dataset, FinQA, with Question-Answering pairs over Financial reports, written by financial experts.” source ↗
-
PortBench
Tests finance“PortBench is a correlation-aware benchmark for LLM-driven portfolio management.” source ↗
-
AfriEconQA
Tests finance“a specialized benchmark dataset for African economic analysis grounded in a comprehensive corpus of 236 World Bank reports” source ↗
-
BlueFin: Benchmarking LLM Agents on Financial Spreadsheets
Tests finance“tasks large language model (LLM) agents with synthesis, manipulation, and comprehension tasks over spreadsheet workbooks in the professional finance domain” source ↗
-
CLQT
Tests finance“A Closed-Loop, Cost-Aware, Strategy-Consistent Benchmark for Diagnostic Evaluation of LLM Portfolio-Management Agents” source ↗
-
FinBen
Tests finance“FinBen serves as the evaluation suite for financial LLMs, with a focus on understanding and prediction tasks across various financial contexts.” source ↗
-
Look-Ahead-Bench
Tests finance“a standardized benchmark measuring look-ahead bias in Point-in-Time (PiT) Large Language Models (LLMs) within realistic and practical financial workflows.” source ↗
-
QFBench
Tests finance“The definitive benchmark for AI agents in quantitative finance. Hard problems. Real code. Verifiable outputs.” source ↗
-
Rogo Big Finance Bench
Tests finance“A 928-question evaluation of how frontier AI agents perform on the work finance professionals actually do.” source ↗
-
BizBench
Tests finance“We introduce BizBench, a benchmark for evaluating models' ability to reason about realistic financial problems.” source ↗
-
ConvFinQA
Tests finance“we investigate the application domain of finance that involves real-world, complex numerical reasoning” source ↗
-
DataClawBench
Tests finance“a benchmark built from financial think-tank consulting scenarios where agents must independently explore unfamiliar, noisy, cross-domain data and produce verifiable conclusions” source ↗
-
FinRED
Tests finance“We introduce FinRED, an expert-guided red-teaming framework for financial LLM safety evaluation developed with financial experts.” source ↗
-
FinRetrieval
Tests finance“We introduce FinRetrieval, a benchmark of 500 financial retrieval questions with ground truth answers” source ↗
-
FinSafetyBench
Tests finance“To systematically evaluate LLM safety in finance, we propose FinSafetyBench” source ↗
-
FinSearchComp
Tests finance“FinSearchComp, the first open-source benchmark specifically designed for open-domain financial search.” source ↗
-
From Knowing to Doing
Tests finance“We introduce KTD-Fin (Knowing-To-Doing Financial Benchmark), an end-to-end stock-market trading benchmark that addresses both issues.” source ↗
-
Herculean
Tests finance“We introduce Herculean, the first skilled benchmark for agentic financial intelligence spanning four representative workflows, including Trading, Hedging, Market Insights, and Auditing.” source ↗
-
INVESTORBENCH
Tests finance“we introduce InvestorBench, the first benchmark specifically designed for evaluating LLM-based agents in diverse financial decision-making contexts.” source ↗
-
IPO Finance Agent
Tests finance“The IPO Finance Agent Benchmark evaluates LLM agents on their ability to analyze IPO filings and perform due diligence using public registration statements.” source ↗
-
K-FinHallu
Tests finance“We introduce K-FinHallu, the first benchmark for hallucination detection in multi-turn Korean financial RAG.” source ↗
-
MacroLens
Tests finance“MacroLens: A Multi-Task Benchmark for Contextual Financial Reasoning under Macroeconomic Scenarios” source ↗
-
PHBench
Tests finance“PHBench: A Benchmark for Predicting Startup Series A Funding from Product Hunt Launch Signals” source ↗
-
QuantEval
Tests finance“We introduce QuantEval, a benchmark that evaluates LLMs across three essential dimensions of quantitative finance” source ↗
-
QuantSightBench
No line from its own site or paper places it in Finance yet; the catalog lists it here.
-
RFC Bench
Tests finance“We introduce RFC Bench, a benchmark for evaluating large language models on financial misinformation under realistic news.” source ↗
-
SECQUE
Tests finance“SECQUE comprises 565 expert-written questions covering SEC filings analysis across four key categories: comparison analysis, ratio calculation, risk assessment, and financial insight generation.” source ↗
-
V4FinBench
Tests finance“we introduce V4FinBench, a benchmark of over one million company-year records from the Visegràd Group (V4) economies (2006-2021)” source ↗
-
FLUE
Tests finance“we contribute the Financial Language Understanding Evaluation (FLUE), an open-source comprehensive suite of benchmarks for the financial domain.” source ↗
-
Open FinLLM Leaderboard
Tests finance“Through comprehensive benchmarking of 30 LLMs across about 50 financial tasks, we aim to help researchers and practitioners identify the right model for their financial applications.” source ↗
-
FinToolBench
Tests finance“we introduce FinToolBench, the first real-world, runnable benchmark dedicated to evaluating financial tool learning agents.” source ↗
-
FiQA 2018
Tests finance“This challenge focuses on advancing the state-of-the-art of aspect-based sentiment analysis and opinion-based Question Answering for the financial domain.” source ↗
-
MortarBench
Tests finance“To fill this gap, we present MortarBench, a loan origination agent benchmark.” source ↗
-
SEC-QA
Tests finance“SEC-QA: A Systematic Evaluation Corpus for Financial QA” source ↗
-
FinBoardBench
Tests finance“FinBoardBench assesses a comprehensive set of financial skills, including personal cash flow management with debt balancing, corporate investment and acquisition forecasting” source ↗
-
InvestPhilBench
Tests finance“no benchmark tests whether they can accurately reconstruct and apply the specific procedural decision frameworks of expert investors” source ↗
4 not yet confirmedListed in the catalog; no line from its own site or paper confirms it yet.
Data 20
- Dissei
- AfterQuery
- Align AI
- Anthromind
-
Aptura
Sells data“Physicians, attorneys, and investment analysts with years of high-stakes experience, supported by a platform built for structured, high-quality data collection at scale.” source ↗
Covers finance“We help train and evaluate AI to master real-world tasks in finance, healthcare, and legal.” source ↗
- Collinear
-
General Reasoning
Sells data“A frozen archive of news, SEC filings, arXiv, Wikipedia and the wider web, with point-in-time search and fetch for forecasting and reproducible evals and training.” source ↗
Covers finance“Every frontier AI model lost money when tasked with betting on Premier League matches over a full season, a new benchmark reveals.” source ↗
- Handshake
- Huzzle Labs
- Mercor
-
micro1
Sells data“We're building the infrastructure for advancing intelligence through expert human data, real-world training environments, and contextual evaluations” source ↗
Covers finance“An evaluation of AI retrieval systems' ability to find and rank authoritative sources for financial research” source ↗
- Patronus AI
-
ReasonCore
Sells data“We produce exclusive and off-the-shelf (OTS) datasets built around multi-step hierarchical reasoning, tool-augmented workflows, and domain-specific problems” source ↗
Covers finance“Specialized economic and financial valuation datasets covering macroeconomic indicators, GDP modeling, financial analysis, and fraud detection.” source ↗
- Revelo
- Snorkel AI
- Surge AI
- Symbal
-
Theta
Covers finance“Generate DCF Model” source ↗
- Turing
- Vetto AI
Next: pick another domain. Tags come from the RL Research daily scrape, canonicalized nightly.