# Finance AI leaderboards

As of 1 Nov 2026, benchmarks.finance tracks 358 sourced scores for 228 models on 38 finance benchmarks. Scores are never combined across benchmarks: every number names its benchmark, its metric and when it was reported.

## Top models by use case

- Analyst research: Deep FinResearch Bench, OpenAI: 86 overall factual claim rate % (Paper Table 7, 22 Apr 2026). https://benchmarks.finance/best/analyst-research/
- Filings Q&A: CorpFin v2, Claude Opus 5: 73.2 accuracy % (Vals.ai leaderboard (archived), 12 Aug 2026). https://benchmarks.finance/best/filings-qa/
- Live market data: CAIA (Crypto AI Agent Benchmark), gpt-5: 67.4 accuracy % (majority vote, 5 runs) (Paper Tables 2-3, 17 Jan 2026). https://benchmarks.finance/best/live-market-data/
- Finance knowledge: Advanced Financial Reasoning at Scale (CFA Level III evaluation), o4-mini: 79.1 overall % (mean of MCQ and essay) (Paper Table 1, 22 Sept 2025). https://benchmarks.finance/best/finance-knowledge/
- Verifiability: ClaimBench, d1-ultra: 100 accuracy % (Vals.ai leaderboard, 23 Oct 2026). https://benchmarks.finance/best/verifiability/
- Advice and safety: FinSafetyBench, LLaMA-3: 32.3 attack success rate % (financial crimes, English) (Paper Table 2, 1 May 2026). https://benchmarks.finance/best/advice-and-safety/
- Trading and portfolios: Agent Market Arena (AMA), InvestorAgent / GPT-4.1: 40.8 cumulative return % (TSLA) (Paper Table 1, 30 Oct 2025). https://benchmarks.finance/best/trading-and-portfolios/
- Spreadsheets and accounting: APEX-Accounting, Gemini 4 Argon: 71.5 Mean Score (% criteria passed) (Mercor APEX-Accounting leaderboard, 1 Nov 2026). https://benchmarks.finance/best/spreadsheets-and-accounting/

## Moneda Bench

- Moneda AdviceBench, first results coming: https://benchmarks.finance/benchmarks/moneda-advicebench/
- Moneda CiteBench, first results coming: https://benchmarks.finance/benchmarks/moneda-citebench/
- Moneda GroundBench, first results coming: https://benchmarks.finance/benchmarks/moneda-groundbench/
- Moneda KnowledgeBench, first results coming: https://benchmarks.finance/benchmarks/moneda-knowledgebench/
- Moneda MarketBench, first results coming: https://benchmarks.finance/benchmarks/moneda-marketbench/
- Moneda PortfolioBench, first results coming: https://benchmarks.finance/benchmarks/moneda-portfoliobench/

## Explore

- Leaderboards: https://benchmarks.finance/leaderboards/
- Benchmark directory: https://benchmarks.finance/benchmarks/
- Compare two models: https://benchmarks.finance/compare/
- Best by use case: https://benchmarks.finance/best/
- Full plain-text listing: https://benchmarks.finance/llms-full.txt

Source: https://benchmarks.finance/

Created and maintained by Moneda.