# Claude Sonnet 4 vs GPT-4.1

Every finance benchmark where both have a score (Anthropic and OpenAI). Data refreshed 2 Nov 2026. Scores from different benchmarks use different scales and are not added up.

| Benchmark | Metric | Claude Sonnet 4 | Claude Sonnet 4 source | GPT-4.1 | GPT-4.1 source | Ahead |
| --- | --- | --- | --- | --- | --- | --- |
| CAIA (Crypto AI Agent Benchmark) | accuracy % (majority vote, 5 runs) (higher is better) | 56.7 | Paper Tables 2-3, 17 Jan 2026, https://arxiv.org/html/2510.00332v2 | 46.6 | Paper Tables 2-3, 17 Jan 2026, https://arxiv.org/html/2510.00332v2 | Claude Sonnet 4 |
| FAITH | overall accuracy % (higher is better) | 95.6 | Paper Table 3, 24 Oct 2025, https://arxiv.org/html/2508.05201v2 | 89.2 | Paper Table 3, 24 Oct 2025, https://arxiv.org/html/2508.05201v2 | Claude Sonnet 4 |

Source: https://benchmarks.finance/compare/claude-sonnet-4-vs-gpt-4-1/

Created and maintained by Moneda.