# GPT-4o vs Qwen2.5-72B-Instruct

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

| Benchmark | Metric | GPT-4o | GPT-4o source | Qwen2.5-72B-Instruct | Qwen2.5-72B-Instruct source | Ahead |
| --- | --- | --- | --- | --- | --- | --- |
| BizFinBench | average score across 9 tasks (higher is better) | 71.8 | Paper Table 3, 26 May 2025, https://arxiv.org/html/2505.19457v1 | 67.7 | Paper Table 3, 26 May 2025, https://arxiv.org/html/2505.19457v1 | GPT-4o |
| InvestorBench | cumulative return % (higher is better) | 39.0 | Paper Table 2, 24 Dec 2024, https://arxiv.org/html/2412.18174v1 | 46.2 | Paper Table 2, 24 Dec 2024, https://arxiv.org/html/2412.18174v1 | Qwen2.5-72B-Instruct |

Source: https://benchmarks.finance/compare/gpt-4o-vs-qwen2-5-72b-instruct/

Created and maintained by Moneda.