Claude Opus 4
Benchmarks scored3
- CAIA (Crypto AI Agent Benchmark)Live financial market data · accuracy % (majority vote, 5 runs) · 17 Jan 2026
- 57.3#4 of 10
- Advanced Financial Reasoning at Scale (CFA Level III evaluation)Finance knowledge · overall % (mean of MCQ and essay) · 22 Sept 2025
- 74.9#4 of 8
- LiveTradeBenchFinancial trading and portfolios · cumulative return % · 5 Nov 2025
- 3.9#8 of 10