GDPval
Professional Work · 2025-09-25
OpenAI's GDPval benchmark of economically valuable knowledge-work tasks across 44 occupations, graded by expert human reviewers via blind pairwise comparison. The score is the rate at which a model's deliverables win or tie against human experts.
Top models (higher is better)
| Model | Score |
|---|---|
| GPT-5.5 | 84.9 |
| GPT-5.4 | 83.0 |
| GPT-5.5 Pro | 82.3 |
| GPT-5.4 Pro | 82.0 |
| Opus 4.7 | 80.3 |
| GPT-5.2 Pro | 74.1 |
| GPT-5.2 | 70.9 |
| GPT-5.3-Codex | 70.9 |
| Gemini 3.1 Pro Preview | 67.3 |
| Opus 4.5 | 45.5 |
| Opus 4.1 | 43.6 |
| Sonnet 4.5 | 42.5 |
| Gemini 3 Pro Preview | 40.3 |
| GPT-5 | 34.8 |
| o3 | 30.8 |
| O4 Mini | 25.3 |
| Gemini 2.5 Pro | 23.3 |
| GPT-4o (2024-11-20) | 9.9 |