# Claude Opus 4 vs gpt-5

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 Opus 4 | Claude Opus 4 source | gpt-5 | gpt-5 source | Ahead |
| --- | --- | --- | --- | --- | --- | --- |
| CAIA (Crypto AI Agent Benchmark) | accuracy % (majority vote, 5 runs) (higher is better) | 57.3 | Paper Tables 2-3, 17 Jan 2026, https://arxiv.org/html/2510.00332v2 | 67.4 | Paper Tables 2-3, 17 Jan 2026, https://arxiv.org/html/2510.00332v2 | gpt-5 |
| LiveTradeBench | cumulative return % (higher is better) | 3.9 | Paper Table 2, 5 Nov 2025, https://arxiv.org/html/2511.03628v1 | 5.3 | Paper Table 2, 5 Nov 2025, https://arxiv.org/html/2511.03628v1 | gpt-5 |

Source: https://benchmarks.finance/compare/claude-opus-4-vs-gpt-5/

Created and maintained by Moneda.